Principal Harness Engineer

🔥 14 minutes ago

🇬🇧 United Kingdom – Remote

⏰ Full Time

🔴 Lead

👷🏻‍♀️ Engineer

👻 Ghost score 10%

What it means: how likely this posting is sitting open without active hiring.How to read it: 60% or higher means we think this is a ghost. Lower scores are less of a worry.How we score it: age, reposts, open roles vs team size, how fast jobs close, and whether pay is listed.Fine print: an estimate from public data, not a judgment of the company. Real jobs can score high, so treat it as a hint, not a fact.

Apply Now

Find Similar Remote Jobs

Set Up Email Alert For New Jobs

📊 Check your resume score for this job

Improve your chances of getting an interview by checking your resume score before you apply.

Upload Resume

FICO

WebsiteLinkedInAll Job Openings

1001 - 5000 employees

Founded 1956

💼 Consulting

🛡️ Insurance

🏥 Healthcare

Consulting • Insurance • Healthcare

FICO is a leading analytics and software company renowned for its FICO® Score, a tool widely used by lenders to assess credit risk. The company offers a comprehensive platform that leverages data, AI, and machine learning to power intelligent decision-making and customer engagement across various industries. FICO's solutions span fraud detection, credit scoring, and customer lifecycle management, making it vital to sectors such as finance and telecommunications. Its innovative products help businesses optimize outcomes through real-time analytics, business composability, and scenario management.

📋 Description

• Design, build, deploy, and support core harness components, including guides, feedback loops, guardrails, and shared context • Own and evolve feedforward guides, agent instruction files, reusable skills, architectural rules, reference documents, and codemods • Drive team-wide standardisation for AI-agent outputs • Build feedback sensors such as custom linters, static analysis, architecture-fitness tests, verification loops, and LLM-as-judge reviewers • Own quality gating and release criteria for agent-produced work • Define authority boundaries for unaided agent merges and escalation rules for human review • Establish LLM testing infrastructure and evaluation approaches for AI-generated output • Apply consumer/contract testing where service integration reliability matters • Run the steering loop to prevent repeated agent mistakes and maintain repository knowledge • Decide where controls run across the path to production • Improve observability into agent work and track measures such as cost per merged PR, time-to-merge, review velocity, defect escape rate, and agent-PR survival rate • Partner with product and platform teams to turn specifications and acceptance criteria into enforceable controls • Serve as a technical expert and mentor engineers in harness practices and responsible AI-tool use

🎯 Requirements

• Bachelor's/Master's in Computer Science or related disciplines, or relevant commercial experience in software architecture, design, development, and testing • Experience as a seasoned software engineer with large, complex codebases • Strong foundation in architecture and design • Hands-on experience with AI coding agents such as Claude Code, Codex, or similar • Experience building engineering tooling across a modern stack, including linters, static analysis, CI/CD pipelines, containerised build/test environments, and instrumentation/observability • Familiarity with agent instruction conventions such as AGENTS.md • Experience with spec-driven development, context engineering, agent orchestration, fitness functions, and developer-platform work • Ability to encode quality standards into mechanical, repeatable rules • Judgement regarding deterministic computational controls versus inferential LLM-based controls, including cost, speed, and reliability trade-offs • Experience owning quality-gating processes and defining release criteria • Working knowledge of autonomous-agent security, including prompt injection, tool/permission scoping, sandboxed execution, and audit trails • Experience with consumer/contract testing approaches such as Pact • Excellent communication skills and ability to articulate designs with architects and drive standards across teams

🏖️ Benefits

• Highly competitive compensation, benefits and rewards programs • Work/life balance • Employee resource groups • Social events • Valuable learning experiences • Professional development opportunities • Inclusive, people-first work environment