Artificial Intelligence Engineer

develop; Greater London; On-site; GBP 85,000 - 140,000; Full time

Job summary

develop is seeking an experienced AI Engineer / LLM Engineer to design and build production-ready AI applications, focusing on Generative AI, LLMs, RAG and agent-based workflows. This is about turning cutting-edge AI into reliable, scalable systems for real-world use.

The role requires hands-on work with Python or other modern languages, production APIs, data pipelines and cloud platforms, plus a focus on observability, reliability and guardrails in distributed environments.

Qualifications

• Hands-on experience with generative AI, large language models and production systems.
• Experience designing AI applications, LLM integrations and agent workflows.
• Knowledge of vector databases, knowledge graphs or similar data platforms.

Responsibilities

• Design and build production-grade AI applications across LLMs, RAG and agents.
• Develop and maintain production APIs, data pipelines and cloud deployments.
• Monitor AI systems for reliability, latency, cost and safety.

Skills

Generative AI

Python

RAG

AI agents

Vector databases

Production APIs

AI monitoring

LangChain / SDKs

Tools

OpenAI SDK

LangSmith

AWS

Azure

GCP

Job description

Build the AI systems that make the next generation of intelligent products possible.

This is an opportunity for an experienced AI Engineer / LLM Engineer to join an ambitious AI environment focused on turning the latest advances in Generative AI into reliable, production-grade systems.

This isn't a research role.

It's for someone who enjoys taking LLMs, agents, RAG and emerging AI technologies and making them actually work in production.

The role

The successful candidate will design and build sophisticated AI applications across:

• LLM applications and API integrations
• RAG and retrieval systems
• Vector and graph databases
• Multi-agent and agentic workflows
• Tool calling and agent handoffs
• AI evaluation and observability
• AI reliability and guardrails
• Production APIs and data pipelines

A major part of the role will involve solving the difficult engineering problems that emerge when deploying non-deterministic AI systems at scale - balancing accuracy, reliability, latency and cost.

What they're looking for

They're looking for someone with strong hands‑on experience in:

• Generative AI
• Python or another modern programming language
• RAG
• AI agents / agentic workflows
• Vector databases / knowledge graphs
• Production APIs and cloud platforms
• AI evaluation and monitoring

Experience with LangGraph, LangChain, Claude Agents SDK, OpenAI SDK, Strands, LangSmith, AWS, Azure or GCP would be highly relevant.

Experience within regulated industries such as financial services, healthcare, energy, legal or retail would be particularly interesting, especially where candidates have worked with responsible AI, compliance or security considerations.

Why consider it?

Because this is an opportunity to work on the part of AI that is moving incredibly quickly - turning increasingly capable models into dependable systems that businesses and customers can actually use.

If you're an engineer who is excited by agents, LLMs, RAG and the challenge of making AI production-ready, this is worth a conversation.