Staff Applied AI Engineer

We’re partnering with a growing enterprise software company that is building out a new Applied AI engineering team in the UK.

We’re looking for experienced engineers who have gone beyond AI prototypes and have built, deployed, and improved LLM/AI systems in production.

What you'll work on

Depending on your background, you'll have the opportunity to specialize in areas including:

• Agentic Systems – production agents, tool calling, MCP, orchestration and human-in-the-loop workflows
• Evaluation & Measurement – eval frameworks, golden datasets, LLM-as-a-Judge, regression testing and observability
• AI Platform & Lifecycle – scalable AI infrastructure, model/provider management, monitoring and production reliability
• Knowledge & Retrieval – RAG, hybrid search, reranking, knowledge graphs and semantic models

What we're looking for

We're looking for strong software engineers with meaningful production Applied AI experience. You don't need to be an expert across every area above, but should have deep experience in at least one.

Relevant experience may include

• Python and/or C#
• Production LLM, RAG or agentic systems
• Backend APIs and distributed systems
• LangGraph, MCP or similar agent frameworks
• Langfuse, LangSmith, Braintrust or Phoenix
• CI/CD, cloud infrastructure and observability

Most importantly, we're looking for people who understand the full production AI lifecycle - building, deploying, evaluating, monitoring and continuously improving AI systems based on real-world performance.

This is a hands-on engineering role with significant technical ownership and the opportunity to help shape a new Applied AI team from the ground up.

If you've taken AI systems from “it works in a demo” to “it works reliably in production,” we'd love to hear from you.

#J-18808-Ljbffr