Senior Applied AI Engineer - Build & Optimize LLM Pipelines

Xapien; Greater London; On-site; GBP 90,000 - 150,000; Full time

Benefits offered by this job

Private health insurance

Life Insurance

Unlimited holidays

£1k professional development fund

Employee equity

Job summary

Xapien is seeking a hands-on AI engineer/researcher in Greater London to own parts of the pipeline end-to-end—from LLM research agents to report generation. You will design evals, optimize for accuracy, speed and cost, and drive improvements.

You'll thrive in a fast-moving startup, ship production systems, and shape what comes next with high ownership. The role focuses on real customer value, prompt engineering, and building trust through robust, scalable AI solutions.

Qualifications

• Strong numerical reasoning and top-tier CS/math/engineering background.
• Shipped production LLM systems—RAG, prompting, and agents.
• Experience in fast-moving startup or tech teams.

Responsibilities

• Own parts of the Xapien pipeline end-to-end — LLM research agents, entity resolution, report generation.
• Build a system optimised for accuracy, speed and cost.
• Design evals that measure what matters, driving meaningful improvements.
• Dig into failures and fix them at the root.
• Shape and ship what's next - high ownership.

Skills

Claude Code

Numerical reasoning

Shipped LLM systems

Startup experience

Software engineering

High ownership

Education

Top-tier CS / maths / engineering / science

Tools

RAG systems

Prompting

Agents

Job description

Xapien is seeking a hands-on AI engineer/researcher in Greater London to own parts of the pipeline end-to-end—from LLM research agents to report generation. You will design evals, optimize for accuracy, speed and cost, and drive improvements.

You'll thrive in a fast-moving startup, ship production systems, and shape what comes next with high ownership. The role focuses on real customer value, prompt engineering, and building trust through robust, scalable AI solutions.