Senior Harness Engineer: AI Quality & Safety

FICO; Frome; On-site; GBP 90,000 - 120,000; Full time

Job summary

FICO is seeking a Senior Harness Engineer in the UK to own harness subsystems and set engineering standards. You will steward end-to-end processes turning raw model capability into production-grade output, with a focus on verification, trust, and repeatable rules.

You’ll work across product and platform teams to codify acceptance criteria, build observability, and mentor engineers in harness practices and responsible AI tool use.

Qualifications

• Bachelor’s/Master’s in Computer Science or related disciplines or relevant commercial experience.
• Experience with AI coding agents and large codebases.
• Proven ability to build engineering tooling across a modern stack (linters, CI/CD, containerised environments).
• Excellent communication skills; able to articulate design with architects.

Responsibilities

• Design, build, and support core components of the harness – the guides, feedback loops, guardrails, and shared context that turn raw model capability into production-grade engineering.
• Own and evolve feedforward guides – agent instruction files, reusable skills, architectural rules, reference docs, and codemods.
• Build feedback sensors – linters, static analysis, tests, and verification loops.
• Own quality gating and release criteria for agent-produced work.
• Establish LLM testing infrastructure and evaluation approaches (e.g., Pact).
• Run the steering loop to prevent repeated mistakes and manage knowledge as the system of record.
• Decide where each control runs in the path to production for efficiency.
• Improve observability and track measures like time-to-merge and defect escapes.

Skills

AI coding agents

Large codebases

Architecture & design

Testing & maintainability

CI/CD pipelines

Observability tooling

Education

Bachelors/Masters in CS

Tools

Claude Code

Codex

Job description

FICO is seeking a Senior Harness Engineer in the UK to own harness subsystems and set engineering standards. You will steward end-to-end processes turning raw model capability into production-grade output, with a focus on verification, trust, and repeatable rules.

You’ll work across product and platform teams to codify acceptance criteria, build observability, and mentor engineers in harness practices and responsible AI tool use.