> Markdown version of [/jobs/ext/3944958-ai-ml-engineer](https://www.wearedevelopers.com/jobs/ext/3944958-ai-ml-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# AI/ML Engineer

- **Company:** Harnham
- **Location:** London, UK
- **Salary:** £100,000.0 - £130,000.0
- **Contract:** Permanent contract
- **Skills:** LangGraph Framework, Artificial Intelligence, Encodings, Cursor, Information Retrieval, Python (Programming Language), Neo4j, Performance Tuning, Search Technologies, Software Deployment, Software Engineering, Systems Integration, Qdrant, Cloud Platform System, Retrieval-Augmented Generation, Large Language Models, Claude Code, Multi-Agent Systems, Model Validation, Langfuse — LLM Observability and Analytics Platform, Pgvector, LangSmith, Kubernetes, Low Latency, Weaviate, Machine Learning Operations, Virtual Agents, Graph RAG
- **Published:** October 27, 2026
- **Apply:** https://www.adzuna.co.uk/jobs/details/5942768514

## About the Role

The successful AI/ML Engineer will have the following skills and experience:

 * Strong Python software engineering expertise
 * Commercial experience developing and deploying LLM or machine learning systems
 * Hands-on experience with LangGraph, LangChain or similar agent orchestration frameworks
 * Strong RAG experience, including embeddings, chunking strategies, vector databases and retrieval evaluation
 * Understanding of graph-based retrieval approaches or graph data modelling principles
 * Experience with evaluation-led AI development, testing frameworks and regression controls
 * Regular use of AI-assisted development tools such as Cursor, Claude Code or similar
 * Ability to balance model performance, reliability, security and operating costs in production systems

Desirable skills include:

 * Qdrant, Weaviate or pgvector
 * Neo4j, GraphRAG and Cypher
 * MCP server development
 * LangSmith, LangFuse or similar observability platforms
 * Fine-tuning, embedding model selection or open-weight model deployment
 * Experience working with complex document-heavy environments

## Description

As a AI/ML Engineer, you will help design, build and operate the LLM-powered systems at the core of the platform, taking AI products from experimentation to reliable production deployment.

Specifically, you can expect to be involved in the following:

 * Building multi-step AI agent workflows using modern orchestration frameworks
 * Developing production-scale retrieval augmented generation (RAG) systems
 * Creating evaluation frameworks, testing infrastructure and monitoring capabilities for AI applications
 * Designing retrieval pipelines including embeddings, vector search, reranking and knowledge retrieval
 * Working with graph-based retrieval and data modelling approaches
 * Optimising AI systems for accuracy, latency, scalability and cost efficiency
 * Integrating leading foundation models into production environments
 * Collaborating closely with engineering leadership to shape technical direction
 * Mentoring engineers and helping establish best practices for AI development at Lead level
 * Contributing across the full software development lifecycle using Python and cloud-based infrastructure