Lead Harness AI Engineer

FICO; United States; On-site; USD 180,000 - 260,000; Full time

Job summary

FICO is seeking a Lead Harness Engineer to own and build the harness that steers AI-generated code toward correct, maintainable output. You’ll work end-to-end from problem framing to production, designing controls, feedback loops, and guardrails that reduce human review.

You will lead the development of feedforward guides, feedback sensors, and steering mechanisms while ensuring observability, performance, and safety in a rapidly evolving AI-enabled software environment.

Qualifications

• Bachelor’s/Master’s in Computer Science or related experience.
• Strong software engineering background with large codebases.
• Experience with AI coding agents and tooling in modern stacks.
• Ability to design, implement, test, and maintain harness components.

Responsibilities

• Design, develop, deploy, and support harness components.
• Build feedforward guides and reusable rules for agents.
• Create feedback sensors and verification tests.
• Run the steering loop to prevent repeated mistakes.
• Contribute to quality gates, release criteria, and AI testing.
• Improve observability and track key metrics.
• Mentor junior engineers and stay current with techniques.

Skills

Software engineering

CI pipelines

Observability

Static analysis

Code review

Communication

Education

Bachelor’s/Master’s in Computer Science

Tools

Agent instruction conventions (AGENTS.md)

Job description

Come join our engineering team in a hands-on technical role at the heart of a new discipline: Harness Engineering. As AI coding agents take on more of the software lifecycle, the hard part is no longer writing code — agents generate it faster than humans can review it, so the bottleneck shifts to verification and trust. Harness Engineering exists to break that bottleneck: engineering the environment that steers agents toward correct, maintainable, well-architected output so that quality is enforced by the system, not re-audited by a person on every change.

We call that environment the harness (Agent = Model + Harness). As a Lead Harness Engineer you'll build and own the individual controls that make up that harness, working end-to-end from problem to production.

This position is not eligible for Visa sponsorship.

What You’ll Contribute

• Design, develop, deploy, and support components of the harness — the guides, feedback loops, guardrails, and shared context that turn raw model capability into production-grade engineering. This is a hands-on role focused on systems and leverage, not hand-writing application code.
• Build feedforward guides — agent instruction files, reusable skills, architectural rules, reference docs, and codemods — that help agents get it right the first time.
• Build feedback sensors — custom linters, static analysis, structural and architecture-fitness tests, verification loops, and LLM-as-judge reviewers — that catch issues before they reach human reviewers.
• Run the steering loop — when an agent repeats a mistake, engineer a control so it can't happen again — and help keep repository knowledge (docs, specs, context) legible to agents, fighting drift.
• Contribute to quality gating and release criteria, and to LLM testing that ensures AI-generated output meets quality and safety thresholds.
• Help improve observability into agent work and track the measures that matter — cost per merged PR, time-to-merge for agent-assisted PRs, review velocity relative to PR size, defect escape rate, and agent-PR survival rate.
• Evaluate the stability, compatibility, scalability, interoperability, and performance of harness components.
• Continually learn new techniques in agent-augmented engineering and serve as a source of technical expertise and mentor to junior team members.

What We’re Seeking

• Bachelor’s/Master’s in Computer Science or related disciplines, or relevant experience in software architecture, design, development, and testing.
• Strong software engineering background; you’ve worked in large codebases and care about architecture, testing, and maintainability.
• Comfortable building tooling across a modern stack — linters and static analysis, CI pipelines, containerized build/test environments, and instrumentation/observability — and familiar with agent instruction conventions such as AGENTS.md.
• Hands‑on experience with AI coding agents (e.g. Claude Code, Codex, or similar) and a feel for where they succeed and fail.
• Experience with spec-driven development, context engineering, agent orchestration, fitness functions, and developer-platform work.
• A systems mindset — you’d rather fix the environment than fix one output — and the ability to encode "what good looks like" into mechanical, repeatable rules.
• Judgement about when to reach for deterministic, computational controls (type checkers, linters, structural/architecture-fitness tests) versus inferential, LLM-based ones (AI code review, LLM-as-judge) — and an understanding of the cost, speed, and reliability trade-offs between them.
• Clear communicator; able to articulate design with architects and discuss strategy and requirements with teams.