Description

The Opportunity

Come join our Software 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 Senior Harness Engineer (Band D2), you’ll independently own whole harness subsystems, set the standards other engineers build to, and be involved in the end-to-end lifecycle of turning raw model capability into production-grade engineering.

What You’ll Contribute

• Design, build, deploy, and support core 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.
• Own and evolve feedforward guides — agent instruction files, reusable skills, architectural rules, reference docs, and codemods — and drive team-wide standardization so 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 automatically before they reach human reviewers.
• Own quality gating and release criteria for agent-produced work, defining authority boundaries for what agents may merge unaided and the escalation rules for what must route to a human.
• Establish LLM testing infrastructure and evaluation approaches that ensure AI-generated output meets quality and safety thresholds; apply consumer/contract testing (e.g. Pact) where service integration reliability matters.
• Run the steering loop — when an agent repeats a mistake, engineer a control so it can’t happen again — deciding where each control runs in the path to production (fast pre-commit checks, heavier post-integration checks, or continuous drift-scanning sensors) to keep quality as far left as is economical, while treating repository knowledge as the system of record and fighting drift with continuous garbage collection.
• 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 — using them to decide where to invest next.
• Partner with product and platform teams to turn specifications and acceptance criteria into enforceable controls.
• Serve as a source of technical expertise and mentor engineers across teams in harness practices and the effective, responsible use of AI tools.

What We’re Seeking

• Bachelor’s/Master’s in Computer Science or related field, or equivalent experience in software architecture, design, development, and testing, with a strong track record in large, complex codebases.
• Hands-on experience with AI coding agents (e.g. Claude Code, Codex, or similar), including building your own tooling or harnesses to make AI agents genuinely effective — not just using them as a power user.
• Proven ability to build engineering tooling across a modern stack, including linters, static analysis, CI/CD pipelines, containerized build/test environments, and instrumentation/observability.
• Experience with spec-driven development, context engineering, agent orchestration, and fitness functions, with a systems mindset that favors fixing the environment over fixing individual outputs.
• Judgment in choosing between deterministic controls (type checkers, linters, structural tests) and inferential, LLM-based controls (AI code review, LLM-as-judge), understanding the trade-offs between them.
• Experience owning quality-gating processes and defining release criteria to ensure engineering standards are consistently met.
• Working knowledge of the security surface unique to autonomous agents — prompt injection, tool/permission scoping, sandboxed execution, and audit trails — and designing least-privilege guardrails around them.
• Experience with consumer/contract testing approaches (e.g. Pact) to validate service integrations across distributed systems.
• Excellent communication skills, with the ability to articulate design decisions, drive standards across teams, and evangelize best practices while incorporating feedback from internal users

Key Skills

Education

Any Graduate