Get Started
Hunting for you, 24x7Get the iPhone app

Your hunt runs in your pocket, and tells you the moment a strong match opens.

Download on theApp Store
FICOPosted in November 2026

Principal Harness Engineer

Who we'd reach at FICOFound and reached by Power Apply
Best leadEngineering lead

Leads the team you would join

CTO

Signs off on engineering hires

Technical recruiter

Owns the opening

Power Apply

From your own Gmail and LinkedIn.

About the role

This is a remote, full-time, senior-level engineering role in the UK at FICO, an analytics software company. The role is a hands-on technical position in harness engineering, a discipline focused on building the environment that steers AI coding agents toward correct and maintainable output. The premise is that writing code is no longer the bottleneck, so verification and trust must be enforced by the system rather than by manual review of every change. You would own harness subsystems independently and set the standards other engineers build to.

What you’ll do

  • Design, build, deploy and support the core parts of the harness: guides, feedback loops, guardrails and shared context.
  • Own agent instruction files, reusable skills, architectural rules, reference docs and codemods, and standardize them across teams.
  • Build automated feedback sensors such as custom linters, static analysis, architecture fitness tests and LLM-based reviewers.
  • Define quality gates and release criteria for agent-produced work, including what agents may merge unaided and what must go to a human.
  • Create testing and evaluation infrastructure for AI-generated output, including consumer contract testing with tools such as Pact where relevant.
  • Turn repeated agent mistakes into engineered controls and keep repository documentation from drifting.
  • Decide where each check runs in the delivery path, from pre-commit checks to continuous drift scanning.
  • Build observability for agent work and track measures such as cost per merged pull request and agent pull request survival rate.
  • Work with product and platform teams to turn specifications into enforceable controls.
  • Mentor engineers on harness practices and the responsible use of AI tools.

What they’re looking for

  • A bachelor's or master's in computer science or a related field, or equivalent commercial experience in architecture, design, development and testing.
  • Experience working in large, complex codebases with a strong grounding in architecture.
  • Hands-on experience with AI coding agents such as Claude Code or Codex.
  • Experience building engineering tooling across a modern stack: linters, static analysis, CI/CD, containerized build and test environments, and 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.
  • Judgement about when to use deterministic controls versus LLM-based controls, including their cost, speed and reliability trade-offs.
  • Experience owning quality gating processes and defining release criteria.
  • Working knowledge of agent-specific security risks such as prompt injection, tool permission scoping, sandboxed execution and audit trails.
  • Experience with consumer contract testing approaches such as Pact.
  • Strong communication skills for articulating design to architects and driving standards across teams.

What’s on offer

  • Compensation, benefits and rewards that the posting describes as highly competitive.
  • Learning opportunities and professional development.
  • Work-life balance, employee resource groups and social events.

Skills

Harness engineeringAI coding agentsClaude CodeCodexAGENTS.mdStatic analysisLintersCI/CDPactArchitecture fitness functionsLLM evaluationObservabilitySpec-driven developmentContext engineeringAgent orchestrationContainerization

Questions about this role

Is this role remote?

Yes, it is listed as remote and based in the UK.

What experience is required?

Experience with large codebases, architecture, testing, AI coding agents and quality gating. A computer science degree or equivalent commercial experience is asked for.

What is harness engineering?

The posting defines the harness as the set of guides, feedback loops, guardrails and shared context that steers AI agents toward correct output.