Senior Harness Engineer

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 Senior Harness Engineer 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 standardisation 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 - and treat repository knowledge (docs, specs, context) as the system of record, fighting drift with continuous garbage collection.
• Decide where each control runs in the path to production - fast checks pre-commit, more expensive checks post-integration, and continuous sensors that scan for drift outside the change lifecycle - keeping quality as far left as is economical.
• 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 disciplines, or relevant experience in software architecture, design, development, and testing.
• Seasoned software engineer with experience in large, complex codebases and a strong foundation in architecture and design; you care deeply about testing and maintainability.
• 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.
• Proven ability to build engineering tooling across a modern stack - linters and static analysis, CI/CD pipelines, containerised 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 - 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.
• 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 for agent actions - and how to design least-privilege guardrails around them.
• Experience with consumer/contract testing approaches (e.g. Pact) to validate service integrations across distributed systems.
• Excellent communication skills; able to articulate design with architects and drive standards across teams.