AI ENGINEER Agentic AI · LangGraph · Multi-Agent Systems · Cloud-Native

ROLE SPECIFICATION · BANKING TECHNOLOGY

We are seeking a highly skilled AI Engineer to join our team and drive innovation in Generative AI, Natural

Language Processing (NLP), and Agentic AI. This role focuses on building production-grade agentic AI systems

leveraging large language models. The AI Engineer will own the development of agent-to-agent architectures,

LangGraph workflows, MCP-based state management, and OpenAI SDK integration to deliver scalable,

business-ready AI applications that transform user experiences and business processes.

Agentic AI LangGraph / OpenAI

SDK Multi-Agent Architecture

Cloud (AWS/Azure/GCP)

Production AI Systems

CORE SKILLS & TECHNOLOGY

Agentic AI Frameworks

■ LangGraph and OpenAI SDK — hands-on experience designing, building, and maintaining agentic AI systems ■ Agent-to-agent communication patterns and multi-agent coordination ■ MCP-based state management and workflow orchestration

NLP & Model Engineering

■ Large Language Model (LLM) integration and prompt engineering ■ RAG pipelines: document chunking, embedding generation, retrieval evaluation ■ Transformer architectures and NLP pipeline design ■ Guardrails, observability tooling, and fallback mechanism design

Programming & Systems

■ Strong Python skills with emphasis on asynchronous programming ■ Distributed systems fundamentals for robust AI architecture deployment ■ Node.js (Express/NestJS) — REST/GraphQL API design and integration ■ Docker, Kubernetes, and IaC for cloud-native AI deployments

Cloud & Infrastructure

■ AWS, Azure, GCP, IBM Cloud — AI application development and deployment ■ Azure AI Foundry, AWS SageMaker, and managed AI/ML services ■ Scalable, secure, and cost-efficient cloud architecture design ■ CI/CD pipelines, monitoring, and observability for AI workloads

WHAT YOU'LL DO

■ Design and implement advanced multi-agent, agent-to-agent AI architectures that enable autonomous and coordinated workflows. ■ Build and manage LangGraph for building agentic framework. ■ Develop and maintain agent to agent communication framework. ■ Architect and implement robust Retrieval-Augmented Generation (RAG) pipelines, including document chunking, embedding generation, and retrieval evaluation to enhance knowledge access. ■ Implement comprehensive guardrails, observability tools, and fallback mechanisms to ensure system resilience, reliability, and safe operation. ■ Optimise AI systems for low latency, high reliability, scalability, and cost efficiency, suitable for production environments.

■ Build and operate cloud-native services on AWS/Azure/GCP/IBM, leveraging managed services, IaC, containerisation (Docker), and orchestration (Kubernetes) where appropriate. ■ Collaborate on API design and integration, working with Node.js services (e.g., Express/NestJS) to expose and consume REST/GraphQL endpoints for agent workflows. ■ Collaborate with cross-functional teams to integrate AI agents with large language models (LLMs), enabling dynamic decision-making and context-aware workflows. ■ Apply expertise in NLP and transformer architectures to engineer intelligent conversational agents that deliver seamless interactions. ■ Stay current with emerging trends and technologies in Agentic AI, LangGraph, LangChain, and related frameworks to continuously innovate and improve system capabilities.

MUST-HAVE SKILLS

Skill Area Requirement

Agentic AI Frameworks Hands-on experience designing, building, and maintaining agentic AI systems using frameworks such as LangGraph/OpenAI SDK, with strong knowledge of agent-to-agent communication patterns.

Programming Strong Python skills with emphasis on asynchronous programming to develop scalable, production-grade AI systems.

Distributed Systems Solid understanding of distributed system fundamentals, enabling robust deployment and scaling of AI architectures.

Cloud Proven experience developing AI applications in cloud environments (AWS, Azure, GCP, IBM Cloud), ensuring reliability, scalability, and security.

NICE-TO-HAVE SKILLS

Skill Area Requirement

Foundational ML & Statistics

Basic knowledge of machine learning concepts and statistics sufficient for collaborating with data science teams and understanding model behaviour.

Frontend / API Integration Experience with frontend frameworks or API development (e.g., Node.js, React.js) to support integration of AI systems into user-facing applications.

Domain Knowledge Familiarity with finance, banking, or enterprise systems to better align AI solutions with business needs.

Role Specification prepared and presented by Pynestone Digital · Your delivery partner in financial services

Lead Backend Engineer

Location: London | Full-time

About LightWork AI LightWork AI is building the operating system for modern property management. Our platform, Felicity, is an intelligent AI assistant that automates the operational workload that slows down property managers, letting agents and build-to-rent teams. Felicity manages communications, compliance, maintenance coordination and scheduling — enabling property businesses to operate with the efficiency of modern digital platforms. The UK property management services industry is undergoing a structural shift toward automation. Property teams currently spend up to 75% of their time on repetitive operational admin, and our AI is designed to automate up to 80–90% of these workflows. We are already live with pilot customers, with overwhelmingly positive feedback and strong demand for the product as we scale toward revenue in 2026. LightWork AI is backed by experienced founders, industry advisors, and investors, and we are building toward a clear goal: to create the defining AI platform for property operations and build a unicorn company in the process. This is a rare opportunity to join early and help shape the technical backbone of a fast-scaling AI company.

The Role We are looking for a Lead Backend Engineer to own and lead the development of the backend systems that power LightWork AI's platform. This is a senior, hands-on engineering leadership role. You will design and build the scalable APIs, services, and integrations that underpin Felicity — our AI-powered property management assistant — while setting the technical direction and standards for the backend engineering team. You will work closely with our AI engineers, data engineers, and product teams to translate complex property workflows into reliable, production-grade systems. As a lead, you will also mentor other engineers and contribute meaningfully to architecture decisions across the stack. This role is ideal for a technically strong engineer who is equally comfortable writing great code and driving engineering culture in a fast-moving startup environment.

Key Responsibilities

Backend Architecture & Engineering • Architect, design, and build scalable backend systems and APIs using Node.js and

TypeScript. • Design and maintain microservice and event-driven architectures that support

Felicity's real-time operational workflows. • Build and maintain RESTful APIs used by internal systems and customer-facing

applications. • Develop and maintain data pipelines and background job systems that process

operational events across property workflows. • Integrate backend services with AI models, LLMs, and automation workflows. • Ensure systems are secure, performant, reliable, and maintainable at scale.

Engineering Leadership • Contribute to technical strategy and architecture decisions across the engineering

team. • Mentor and support backend engineers, fostering a high-performing team culture. • Lead and participate in code reviews, setting high standards for code quality and

testing. • Collaborate with Product, AI, and Data teams to translate business requirements into

well-scoped technical solutions. • Help define and improve development practices, tooling, and engineering workflows.

Reliability & Observability • Deploy, monitor, and maintain production services with a strong focus on uptime and

performance. • Implement logging, observability, and alerting frameworks to ensure system health. • Debug and resolve complex issues across backend systems and third-party

integrations. • Own incident response and post-mortems for backend-related issues.

Requirements

Core Experience • 7+ years of professional backend or full-stack software engineering experience. • Deep expertise in Node.js with TypeScript. • Strong experience designing and building RESTful APIs and backend service

architectures. • Proven experience leading engineering projects or teams, including mentoring more

junior engineers. • Experience building and operating systems in microservice or event-driven

architectures. • Strong understanding of data modelling, storage, and relational databases

(PostgreSQL preferred). • Experience with Git, CI/CD workflows, and modern software development practices. • Comfortable debugging production systems and working with logs and monitoring

tooling.

• Strong problem-solving and system design skills, with the ability to navigate ambiguity in an early-stage environment.

Nice to Have • Production experience building APIs with Python (FastAPI, Flask, or Django). • Experience integrating with AI or LLM-based systems. • Familiarity with stream processing, message queues (e.g. Kafka, RabbitMQ), or

event-driven architectures. • Experience with cloud infrastructure (GCP, AWS, or Azure) and containerised

services (Docker, Kubernetes). • Experience working with vector databases or ML data pipelines. • Familiarity with NestJS or similar backend frameworks. • Previous experience in high-growth startups or early-stage companies.

What We’re Looking For • A senior engineer with genuine ownership mentality — someone who builds things

that last and cares about the craft. • Comfortable leading from the front: making decisions, setting direction, and holding

the bar on quality. • A collaborative team player who works well across functions including product, AI,

and data. • Strong communicator who can translate technical complexity for non-technical

stakeholders. • Excited by the opportunity to build in a fast-moving startup solving a large, real-world

problem.

Why Join LightWork AI • Lead backend engineering at a category-defining AI company from an early stage. • Work directly with the founders and core engineering team with genuine ownership

and influence. • Competitive salary + equity — share in the upside of what we build together. • Shape engineering culture, architecture, and tooling from the ground up. • Build technology that automates and transforms the UK property management

industry.

Lead AI/Python Engineer | Equity + Cash Location: London | Full Time About LightWork AI LightWork AI is a Service-as-a-Software (SaaS) company that automates property management workflows (compliance, maintenance, lettings, and tenant support) through Felicity, an AI assistant capable of handling up to 80% of admin tasks autonomously.

Designed for the UK’s regulation-driven market, LightWork AI delivers enhanced capacity, reduced admin costs and zero missed communications for property management & lettings agencies, while giving tenants the confidence that their homes are safe, compliant and their needs are always met. The Role We are seeking a Lead Python Engineer to join our growing team. This is a high-impact role for a technically strong engineer who thrives on building scalable AI-driven systems, mentoring other engineers, and shaping the engineering practices of a fast-scaling AI startup. You will collaborate closely with Product, AI, software engineers and Design teams to deliver robust backend systems and intelligent software solutions that directly impact the business and end users. Key Responsibilities:

● Architect, design, and build scalable backend systems and APIs using Python. ● Optimize and scale data pipelines for reliability, efficiency, and performance. ● Write, review, and maintain clean, testable code. ● Contribute to technical strategy, architecture decisions, and code reviews. ● Mentor junior engineers and foster a high-performing team culture. ● Collaborate with Product and Design teams to translate business needs into

technical solutions. ● Drive innovation in AI integration, automation, and system scalability. ● Ensure systems are secure, performant, and maintainable.

Requirements:

● First-class or strong degree in Computer Science, Engineering, or related field. ● 3 -10 years of hands-on software engineering experience, ideally in AI, SaaS, or

automation platforms. ● Deep expertise in Python; familiarity with FastAPI, Flask, or Django. ● Experience with Node.js, cloud infrastructure, and microservices-based systems. ● Familiarity with data pipelines, Git, and CI/CD workflows. ● Proven ability to lead projects and mentor engineers. ● Excellent problem-solving, collaboration, and communication skills.

Nice to Have:

● Experience contributing to open-source projects. ● Containerization (Docker/Kubernetes) and microservices architecture experience.

What We Offer:

● Competitive salary and equity options — share in the success you help create. ● Opportunity to shape the engineering culture and technology roadmap from the

ground up. ● Work in a collaborative, mission-driven AI startup redefining property management. ● Be part of a team building AI-driven solutions that directly impact real-world

problems.

Full-Stack Engineer | Pre-Seed AI & Climate Infra | London / Remote | Contract → FT

Tags

Full-Stack Engineer | Pre-Seed AI & Climate Infra | London / Remote | Contract → FT

About Veridue AI / the mission we obsess over Energy is the primary lever for the survival of our planet. The transition to a

zero-carbon economy is the greatest challenge of our generation, touching

everything from global affordability to the massive power demands of the AI

revolution.

Our mission is simple: Abundant, cheap, and clean energy for everyone.

To stay within a livable climate threshold, the world must invest $4 trillion every

single year in energy transition infrastructure: renewables, battery storage, and

EV charging. Currently, we are failing to hit that target.

The bottleneck isn't a lack of capital, the cost of hardware, or the speed of

construction. The bottleneck is automatable processes. On average, it takes five

years to get all the paperwork in place to build a one-year construction project.

The world is building paper stacks, instead of solar racks.

We are building the AI infrastructure to shrink those five years into five

seconds. By automating the most painful, manual bottlenecks in the development

cycle, we unblock the flow of capital to the front lines of the energy transition. Our

current product delivers agentic AI due diligence for renewable energy

Full-Stack Engineer | Pre-Seed AI & Climate Infra | London / Remote | Contract → FT 1

investors. We replace months of manual legal and technical review with a high-

precision AI audit delivered in one hour.

We raised a highly oversubscribed $4M pre-seed round and are backed by

world class investors, including Episode 1, HTGF, PiLabs, Cameron Hepburn 2x

energy unicorn founder), Ian Smedley Barclays Head of Power M&A , Jeremy

Palmer Chairman PhysicsX , and Sam Bourton (ex CTO Quantum Black) amongst

others.

About the founders Daniel, CEO has done over $10 billion in energy M&A transactions both as an

investor at a renewables investment fund in New York and as an advisor at

McKinsey in London and New York. He used to be our ICP, knows the problem

and the industry inside out, has an amazing network in the space, and has earned

his reputation and trust from a decade in the space.

Xander, CTO similarly has led AI risk modeling for over $1 trillion in insured value

of energy assets, working for one of the largest reinsurance companies in the

world SCOR . There, he gained hyper-relevant Agentic AI experience building and

deploying it in production for contract review, a high-stakes environment where

building trust in AI with users is key.

The Role We are looking for an experienced, highly autonomous Full-Stack Engineer to join

us on a contract basis 1 3 months) ASAP, with the possibility to convert into a

full-time role if thereʼs mutual interest.

As an early technical hire, you will work directly with the CTO to build the platform

that powers Veridue's due diligence engine. We need someone comfortable

owning features end-to-end in an early-stage startup environment—moving from

database schema design to frontend implementation with speed and precision.

Example problems you will work on:

Granular Access Controls: Building robust sharing mechanisms and RBAC for

sensitive project data room content.

Full-Stack Engineer | Pre-Seed AI & Climate Infra | London / Remote | Contract → FT 2

Human-in-the-Loop AI Workflows: Creating interfaces where users can

review and edit AI-generated outputs, ensuring version history is captured for

training and feedback loops.

Third-Party Data Integration: Integrating external datasets (e.g., UK Land

Registry) and reconciling them with project documents and data room

materials.

The Veridue Mindset

Obsession with the Energy Transition: We are deeply passionate about

solving climate change by removing the massive bottlenecks in energy

infrastructure. We want to use our engineering skills to accelerate the

deployment of abundant, cheap, and clean energy.

Conscious Evolution: We are building an ambitious business, which requires

us to be at our best. We actively invest in our personal growth through

coaching, therapy, meditation, or deep self-reflection, and support each other

in becoming more authentic and grounded.

AI Native Craftsmanship: We don't just build AI; we build with AI. Itʼs our

force multiplier. We are obsessed with staying at the bleeding edge of agents

and are power users of Claude Code. We donʼt ship AI spaghetti; we control

architecture and ship precision-engineered codebases that happen to be built

at 100x speed.

Systems Thinking from First Principles: We strip complex problems down to

their fundamental truths instead of following standard industry playbooks. We

are systems builders who think in architectural primitives rather than just

tickets or features, designing systems that eliminate months of work.

Impact Over Ego: We measure our success by customer ROI and delight, not

just by building intellectually interesting tech. We leave our egos at the door,

handle radical candor gracefully, and lead from a place of vulnerability and

trust.

Relentless Velocity & Extreme Ownership: If someone says a solution will

take a week, our instinct is to figure out how to ship a high-impact MVP in a

Full-Stack Engineer | Pre-Seed AI & Climate Infra | London / Remote | Contract → FT 3

day. We don't wait for permission; we see a broken process, take ownership

from concept to success, and put in the focused hours when it matters most.

Ideal Profile

Full-Stack Fluency: Highly proficient with our stack: Python, FastAPI,

PostgreSQL, React, TypeScript, Tailwind, shadcn/ui, TanStack

The Veteran: A deep background in hardcore software engineering, capable

of building secure, scalable web applications.

Data-Heavy Pipelines: Experience building pipelines that extract truth from

messy data or multi-thousand-page PDFs.

Founding DNA Youʼve been a founder, an early hire, or have shipped a side

project from 0 to 1. You don't need a spec to get started.

Reliability Obsessed: Deep familiarity with observability, testing, and ensuring

high-stakes financial/legal data is handled correctly.

What We Offer

Immediate Impact: A 1 3 month high-intensity contract with a clear mission.

Remote or Hybrid: Optional 3 days in office in London with the team,

High-Impact Domain: Energy transition infrastructure is one of the most

consequential investment spaces globally.

Technical Autonomy: You'll own architecture decisions and shape the

technical direction for the features you build.

Convert: possibility to convert into a full-time role if thereʼs mutual interest and

you can do 3 days in office.

Interview Process

Pitch: Send us your website, recent work, or a few bullets on why youʼre a fit.

Intro 15 mins): A quick get-to-know-you with Xander CTO .

Technical Deep Dive 45 mins): A peer-to-peer session focusing on full-stack

systems design and implementation.

Full-Stack Engineer | Pre-Seed AI & Climate Infra | London / Remote | Contract → FT 4

Day Zero (paid): Youʼll work on a real problem and ship something. Itʼs the

fastest way to see if our technical gears click.

Full-Stack Engineer | Pre-Seed AI & Climate Infra | London / Remote | Contract → FT 5

Full-Stack AI Engineer | Pre- Seed AI & Climate Infra | London / Remote | Contract → FT

Tags

Full-Stack AI Engineer | Pre-Seed AI & Climate Infra | London / Remote | Contract → FT

About Veridue AI / the mission we obsess over Energy is the primary lever for the survival of our planet. The transition to a

zero-carbon economy is the greatest challenge of our generation, touching

everything from global affordability to the massive power demands of the AI

revolution.

Our mission is simple: Abundant, cheap, and clean energy for everyone.

To stay within a livable climate threshold, the world must invest $4 trillion every

single year in energy transition infrastructure: renewables, battery storage, and

EV charging. Currently, we are failing to hit that target.

The bottleneck isn't a lack of capital, the cost of hardware, or the speed of

construction. The bottleneck is automatable processes. On average, it takes five

years to get all the paperwork in place to build a one-year construction project.

The world is building paper stacks, instead of solar racks.

We are building the AI infrastructure to shrink those five years into five

seconds. By automating the most painful, manual bottlenecks in the development

Full-Stack AI Engineer | Pre-Seed AI & Climate Infra | London / Remote | Contract → FT 1

cycle, we unblock the flow of capital to the front lines of the energy transition. Our

current product delivers agentic AI due diligence for renewable energy

investors. We replace months of manual legal and technical review with a high-

precision AI audit delivered in one hour.

We raised a highly oversubscribed $4M pre-seed round and are backed by

world class investors, including Episode 1, HTGF, PiLabs, Cameron Hepburn 2x

energy unicorn founder), Ian Smedley Barclays Head of Power M&A , Jeremy

Palmer Chairman PhysicsX , and Sam Bourton (ex CTO Quantum Black) amongst

others.

About the founders Daniel, CEO has done over $10 billion in energy M&A transactions both as an

investor at a renewables investment fund in New York and as an advisor at

McKinsey in London and New York. He used to be our ICP, knows the problem

and the industry out, has an amazing network in the space, and has earned his

reputation and trust from a decade in the space.

Xander, CTO similarly has led AI risk modeling for over $1 trillion in insured value

of energy assets, working for one of the largest reinsurance companies in the

world SCOR . There, he gained hyper-relevant Agentic AI experience building and

deploying it in production for contract review, a high-stakes environment where

building trust in AI with users is key.

The Role We are looking for an experienced, highly autonomous Full-Stack AI Engineer to

join us on a contract basis 1 3 months) ASAP, with the possibility to convert into

a full-time role if thereʼs mutual interest.

As a core technical contributor, you will work directly with the CTO to build the

Agentic AI system and platform that powers Veridue's due diligence engine. We

need someone who can bridge the gap between sophisticated AI orchestration

and high-quality product engineering—moving from RAG architecture and agentic

loops to sleek frontend implementation with speed and precision.

Example problems you will work on:

Full-Stack AI Engineer | Pre-Seed AI & Climate Infra | London / Remote | Contract → FT 2

Create AI Subagents that tackle high-stakes due diligence pillars like land

rights analysis or permit matrix extraction from thousands of fragmented

documents.

Elevate our Context Engineering through advanced RAG patterns and

knowledge graphs, mapping and extracting truth across 10,000 document

data rooms.

Human–Agent Collaboration: Think Claude Code for Energy Investors.

Building a seamless interface where the AI acts as a digital colleague. Solve

for knowledge access, contextual UI (where users can right-click any content

to start a chat), linking references back to exact UI sections, and incrementally

modifying diligence outputs.

Note: Across any of these projects, you will be working on cutting-edge AI

implementations, but it will be in the real world of production AI, messy data,

and inconsistent criteria. While we have extensive ground-truth data, you will

be responsible for building your own evals to ensure legal-grade precision.

The Veridue Mindset

Obsession with the Energy Transition: We are deeply passionate about

solving climate change by removing the massive bottlenecks in energy

infrastructure. We want to use our engineering skills to accelerate the

deployment of abundant, cheap, and clean energy.

Conscious Evolution: We are building an ambitious business, which requires

us to be at our best. We actively invest in our personal growth through

coaching, therapy, meditation, or deep self-reflection, and support each other

in becoming more authentic and grounded.

AI Native Craftsmanship: We don't just build AI; we build with AI. Itʼs our

force multiplier. We are obsessed with staying at the bleeding edge of agents

and are power users of Claude Code. We donʼt ship AI spaghetti; we control

architecture and ship precision-engineered codebases that happen to be built

at 100x speed.

Systems Thinking from First Principles: We strip complex problems down to

their fundamental truths instead of following standard industry playbooks. We

Full-Stack AI Engineer | Pre-Seed AI & Climate Infra | London / Remote | Contract → FT 3

are systems builders who think in architectural primitives rather than just

tickets or features, designing systems that eliminate months of work.

Impact Over Ego: We measure our success by customer ROI and delight, not

just by building intellectually interesting tech. We leave our egos at the door,

handle radical candor gracefully, and lead from a place of vulnerability and

trust.

Relentless Velocity & Extreme Ownership: If someone says a solution will

take a week, our instinct is to figure out how to ship a high-impact MVP in a

day. We don't wait for permission; we see a broken process, take ownership

from concept to success, and put in the focused hours when it matters most.

Ideal Profile

Full-Stack Fluency: Highly proficient with our stack: Python, FastAPI,

PostgreSQL, React, TypeScript, Tailwind, shadcn/ui, TanStack.

AI Orchestration: Experience building custom loops for agentic memory, tool-

use, and state management (beyond simple API wrappers).

Data-Heavy Pipelines: Experience building pipelines that extract truth from

messy data or multi-thousand-page PDFs.

Founding DNA Youʼve been a founder, an early hire, or have shipped a side

project from 0 to 1. You don't need a spec to get started.

Reliability Obsessed: Deep familiarity with observability, testing, and ensuring

high-stakes financial/legal data is handled correctly.

What We Offer

Immediate Impact: A 1 3 month high-intensity contract with a clear mission.

Remote or Hybrid: Optional 3 days in office in London with the team.

High-Impact Domain: Energy transition infrastructure is one of the most

consequential investment spaces globally.

Technical Autonomy: You'll own architecture decisions and shape the

technical direction for the features you build.

Full-Stack AI Engineer | Pre-Seed AI & Climate Infra | London / Remote | Contract → FT 4

Convert: Possibility to convert into a full-time role if thereʼs mutual interest and

you can do 3 days in office.

Interview Process

Pitch: Send us your website, recent work, or a few bullets on why youʼre a fit.

Intro 15 mins): A quick get-to-know-you with Xander CTO .

Technical Deep Dive 45 mins): A peer-to-peer session focusing on full-stack

systems design and AI implementation.

Day Zero (paid): Youʼll work on a real problem and ship something. Itʼs the

fastest way to see if our technical gears click.

Full-Stack AI Engineer | Pre-Seed AI & Climate Infra | London / Remote | Contract → FT 5

About Decagon

Decagon is the leading conversational AI platform empowering every brand to deliver concierge customer experience. Our AI agents provide intelligent, human-like responses across chat, email, and voice, resolving millions of customer inquiries across every language and at any time.

Since coming out of stealth, Decagon has experienced rapid growth. We partner with industry leaders like Hertz, Eventbrite, Duolingo, Oura, Bilt, Curology, and Samsara to redefine customer experience at scale. We've raised over $200M from Bain Capital Ventures, Accel, a16z, BOND Capital, A*, Elad Gil, and notable angels such as the founders of Box, Airtable, Rippling, Okta, Lattice, and Klaviyo.

We’re an in-office company, driven by a shared commitment to excellence and velocity. Our values—customers are everything, relentless momentum, winner’s mindset, and stronger together—shape how we work and grow as a team.

About the Team

The Research team at Decagon innovates on building the most advanced conversational AI agents for enterprise customers. Decagon’s AI agents understand context, respond with genuine empathy, and solve complex problems with surgical precision.

Our mission is to deliver magical support experiences — AI agents working alongside human agents to help users resolve their issues.

About the Role

On the Research team, you’ll be responsible for building AI systems that can perform previously impossible tasks or achieve unprecedented levels of performance. You will design and implement state of the art methods for instruction tuning and information retrieval. We're looking for people with strong engineering skills, writing bug-free

machine learning code, and building the science behind the algorithms that power our AI agents.

Engineers here own their work end-to-end and are trusted to make a real impact. This role is for someone who dives deep into complex system challenges, builds elegant solutions that scale to millions of users, and creates automation that prevents problems before they happen.

In this role, you will

• Develop models for customer support tasks that exceed the performance of closed source models

• Experiment with small open-source models to drive order of magnitude reductions in latency across channels

• Break down ambiguous research ideas into clear, iterative milestones and roadmaps.

Your background looks something like this

• 3+ years of experience in AI/ML engineering or research.

• Proven track record of working on AI/ML projects from concept to production.

• Experience fine-tuning and deploying LLMs in production environments.

• Prior experience working with multi-modal models

Benefits:

• Medical, dental, and vision benefits

• Take what you need vacation policy

• Daily lunches, dinners and snacks in the office to keep you at your best