Harness Engineer, Director
Level inferred from job title
Job description
Lead a new internal Harness Engineering team at FICO that builds the environment (guides, guardrails, feedback loops, shared context) enabling AI coding agents to produce reliable, production-grade engineering output. Hands-on leadership role designing and building harness components while managing and growing a regional team.
At a glance
- Employment
- Full-time
- Work mode
- Remote
What you'll do
- Help design, build, and evolve the harness: guides, feedback loops, guardrails, and shared context that turn raw model capability into production-grade engineering
- Build and maintain feedforward guides (agent instruction files, reusable skills, architectural rules, reference docs, codemods) and drive their adoption across teams
- Build feedback sensors, custom linters, structural and architecture-fitness tests, verification loops, and LLM-as-judge reviewers that catch issues before human reviewers
- Own AI governance for the region: define authority boundaries for what agents may merge unaided, establish LLM testing infrastructure, ensure AI-generated output meets quality, safety, and compliance thresholds
- Define and own cross-organizational QA and quality-gating standards
- Run the steering loop at scale: engineer controls so repeated classes of agent mistakes cannot happen again; treat repository knowledge as the system of record and fight drift
- Decide where each control runs in the path to production (fast pre-commit checks, more expensive post-integration checks, continuous drift sensors)
- Establish observability into agent work and own measures such as 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
- Manage, coach, and grow a geographically distributed team of harness engineers; partner with stakeholders to attract talent, set goals, and measure and reward performance
- Work with other engineering leaders and product management to turn specifications and acceptance criteria into enforceable controls and align the harness with platform and delivery roadmaps
- Demonstrate expertise through internal enablement, presentations, and thought leadership on agent-augmented engineering
What we're looking for
- Strong software engineering background with experience in large, complex codebases and genuine care for architecture, testing, and maintainability; remains hands-on
- Strong consensus building skills
- Hands-on experience with AI coding agents (e.g. Claude Code, Codex, or similar) and a well-developed feel for where they succeed and fail
- Experience building engineering tooling across a modern stack, linters and static analysis, CI/CD pipelines, containerized build/test environments, and instrumentation/observability, plus familiarity with agent instruction conventions such as AGENTS.md
- Experience with spec-driven development, context engineering, agent orchestration, fitness functions, and developer-platform work
- A systems mindset: prefers fixing the environment over fixing one output; ability to encode 'what good looks like' into mechanical, repeatable rules
- Judgement about when to use deterministic, computational controls (type checkers, linters, structural/architecture-fitness tests) versus inferential, LLM-based ones (AI code review, LLM-as-judge), understanding cost, speed, and reliability trade-offs
- Demonstrated experience owning AI governance and cross-organizational quality standards, including establishing LLM testing infrastructure and quality gating for AI-generated artifacts
- Working knowledge of the security surface unique to autonomous agents: prompt injection, tool/permission scoping, sandboxed execution, and audit trails for agent actions, and designing least-privilege guardrails
- Strong experience managing geographically distributed, high-performing engineering teams, including navigating the organizational change that AI adoption brings
- Excellent communication skills to articulate design, strategy, and standards across teams
- Bachelor's/Master's in Computer Science or related discipline, or relevant experience in software architecture, design, development, and testing
Nice to have
- Ideally a great evangelist: able to build the systems and also go out to the internal user base, evangelise what the team is doing, share benefits, tips and tricks, listen to feedback, and bring it back to the team
Your team
Harness Engineering
A new internal team that owns the harness (Agent = Model + Harness): the guides, feedback loops, guardrails, and shared context that steer AI coding agents toward correct, maintainable, well-architected output.
Benefits
An inclusive culture strongly reflecting core values: Act Like an Owner, Delight Our Customers and Earn the Respect of Others
The opportunity to make an impact and develop professionally by leveraging unique strengths and participating in valuable learning experiences
Highly competitive compensation, benefits and rewards programs that encourage you to bring your best every day and be recognized for doing so
An engaging, people-first work environment offering work/life balance, employee resource groups, and social events to promote interaction and camaraderie
Apply
About FICO
A leading global analytics software company, helping businesses in 100+ countries make better decisions.
FICO (NYSE: FICO) is a leading global analytics software company, helping businesses in 100+ countries make better decisions. FICO makes a real difference in the way businesses operate worldwide through credit scoring, fraud detection and security, and lending solutions.
Mission
Help businesses use data to improve every choice they make, using advances in artificial intelligence, machine learning, optimization, and much more.
Key facts
- Analytics software / Big Data analytics
- FICO® Scores are used by 90 of the top 100 US lenders
- 4 billion payment cards globally are protected by FICO fraud systems
- 3/4 of US mortgages are approved using the FICO Score
- Among the world's top 100 software companies by revenue
- Helps many of the world's largest banks, insurers, retailers, telecommunications providers and other firms
What they value
- Act Like an Owner
- Delight Our Customers
- Earn the Respect of Others