Senior AI Engineer (Full Stack)

Expedeon Inc. (an Abcam company); Cambridge; On-site; GBP 90,000 - 130,000; Full time

Benefits offered by this job

Health care program

Paid time off

Comprehensive benefits package

Job summary

Expedeon Inc. (an Abcam company) in Cambridge is seeking a Senior AI Engineer (Full Stack) to design, evaluate, and operate AI systems built on foundation models, delivering production‑ready apps with measurable business impact.

You will lead end-to-end LLM‑powered applications including RAG and agent workflows, transform prototypes into reliable services with deployment, monitoring, and guardrails, and collaborate with the Data & AI team on scalable solutions.

Qualifications

• Strong software engineering skills, primarily in TypeScript and Python with backend and API development experience.
• GenAI systems: RAG, prompt engineering, LLM integration, and agentic workflows.
• Cloud and infrastructure knowledge: deployment, containerization, and CI/CD practices.
• Understanding of machine learning fundamentals, including model behavior, evaluation, and testing.
• Demonstrated ability to design, deploy, and operate production‑grade AI systems focusing on reliability, scalability, and performance.

Responsibilities

• Design and deliver end‑to‑end LLM‑powered applications, including RAG systems and agent workflows.
• Transform prototypes into reliable, scalable production services with deployment, monitoring, and failure handling.
• Integrate and operate external model APIs, managing latency, cost, and reliability constraints.
• Build and operate data pipelines for retrieval, evaluation, and fine‑tuning workflows.
• Establish evaluation, monitoring, and guardrails to ensure performance, quality, and safety.

Skills

TypeScript

Python

LLM integration

RAG

Agent workflows

CI/CD

Cloud deployment

Monitoring

Production systems

Tools

LangGraph

LangChain

PocketFlow

nx

lerna

Job description

Senior AI Engineer (Full Stack)

Design, evaluate, and operate AI systems built on foundation models, translating model behavior into production‑ready applications that deliver measurable business impact.

Reports to the Senior Director of AI Operations and Commercial. Team: Data & AI, Cambridge. Role is on‑site.

Responsibilities

• Design and deliver end‑to‑end LLM‑powered applications, including RAG systems and agent workflows.
• Transform prototypes into reliable, scalable production services with deployment, monitoring, and failure handling.
• Integrate and operate external model APIs, managing latency, cost, and reliability constraints.
• Build and operate data pipelines for retrieval, evaluation, and fine‑tuning workflows.
• Establish evaluation, monitoring, and guardrails to ensure performance, quality, and safety.

Qualifications

• Strong software engineering skills, primarily in TypeScript and Python with backend and API development experience.
• Expertise in GenAI systems: RAG, prompt engineering, LLM integration, and agentic workflows.
• Cloud and infrastructure knowledge: deployment, containerization, and CI/CD practices.
• Understanding of machine learning fundamentals, including model behavior, evaluation, and testing.
• Demonstrated ability to design, deploy, and operate production‑grade AI systems focusing on reliability, scalability, and performance.

Preferred Experience

• Experience with LangGraph, LangChain, PocketFlow, or other multi‑agent orchestration tooling.
• Familiarity with monorepo technologies (nx, lerna) and multi‑application deployment pipelines.

Benefits

Competitive health care program, paid time off, and a comprehensive benefits package that adds value beyond the job.