Generative AI Engineer

Lorien; Greater London; Hybrid; GBP 65,000 - 90,000; Full time

Job summary

Lorien in London is seeking AI Engineers and Applied AI specialists to join our growing AI function. You will build production-grade LLM and Generative AI applications, develop AI agents and agentic workflows, and design RAG and advanced retrieval solutions.

You will deploy AI applications across cloud environments, implement robust evaluation, monitoring and guardrails, and work with product, engineering and business teams to solve complex problems.

Qualifications

• Hands-on commercial experience with Python.
• Experience with agentic AI / AI agents.
• Experience with RAG techniques and retrieval augmented generation.
• Familiarity with LangChain, LangGraph, LlamaIndex or similar.
• Knowledge of MCP / FastMCP.
• Experience with OpenAI, Claude, Gemini or open-source LLMs.
• Experience with cloud providers (AWS Bedrock, Azure OpenAI, Vertex AI).
• Experience with FastAPI.
• Experience with LLM evaluation and observability.

Responsibilities

• Build production-grade LLM and Generative AI applications.
• Develop AI agents and agentic workflows.
• Design RAG and advanced retrieval solutions.
• Build single and multi-agent architectures.
• Integrate LLMs with enterprise tools, APIs and data.
• Develop robust AI evaluation, monitoring and guardrails.
• Deploy AI applications across cloud environments.
• Collaborate with product, engineering and business teams to solve complex problems.

Skills

Python

Agentic AI

RAG

FastAPI

LLM evaluation

Tools

LangChain

LangGraph

LlamaIndex

MCP

FastMCP

OpenAI

Claude

Gemini

AWS Bedrock

Azure OpenAI

Vertex AI

Job description

Focus:

Agentic AI | LLMs | RAG | Machine Learning

Length

6 months

The opportunity

We're looking for AI Engineers and Applied AI specialists to join a growing AI function focused on building production-grade AI products.

You'll work across LLM applications, AI agents, RAG, intelligent automation and machine learning, taking solutions from initial concept through to deployment, evaluation and continuous improvement.

This is a hands-on environment focused on shipping real-world AI solutions, rather than purely experimentation or proof-of-concepts.

What you'll be doing

• Build production-grade LLM and Generative AI applications
• Develop AI agents and agentic workflows
• Design RAG and advanced retrieval solutions
• Build single and multi-agent architectures
• Integrate LLMs with enterprise tools, APIs and data
• Develop robust AI evaluation, monitoring and guardrails
• Deploy AI applications across cloud environments
• Work closely with product, engineering and business teams to solve complex problems

What we're looking for:

We're interested in candidates with hands-on commercial experience across several of the following:

• Python
• Agentic AI / AI Agents
• RAG
• LangChain, LangGraph, LlamaIndex or similar
• MCP / FastMCP
• OpenAI, Claude, Gemini or open-source LLMs
• AWS Bedrock, Azure OpenAI / AI Foundry or Vertex AI
• FastAPI
• LLM evaluation and observability

Experience with recommendation systems, forecasting, NLP, classification or traditional machine learning would also be valuable.

What we're really looking for:

We're particularly interested in people who have taken AI beyond the PoC stage and into production.

Whether you've built AI agents, enterprise RAG platforms, multi-agent workflows or production LLM applications, we're more interested in what you've built and the problems you've solved than ticking every technology box