Technical Senior Manager, Harness Engineering

Job Summary

Come join our engineering team to build the discipline that lets AI coding agents do reliable work at scale. As 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). This is a hands-on management role: you will personally build harness components while leading and growing a team of harness engineers and governing the responsible use of AI across your team.

What You'll Contribute

• Personally design, build, 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; you will contribute code, not just direct it.
• Build and maintain feedforward guides (agent instruction files, reusable skills, architectural rules, reference docs, and codemods) and feedback sensors (custom linters, architecture-fitness tests, verification loops, and LLM-as-judge reviewers) that help agents get it right the first time and catch issues before they reach human reviewers.
• Drive adoption of AI coding agents and harness practices through hands-on enablement - pairing, office hours, and reference examples - measuring success by active usage, review time saved, and defect escape rate rather than by artifacts shipped.
• Govern responsible AI usage within your team, ensuring engineers apply AI tools appropriately, ethically, and in line with company standards, compliance requirements, and defined quality and safety thresholds.
• Own quality gating and release criteria for your teams work - defining authority boundaries for what agents may merge unaided and the escalation rules for what must route to a human.
• Run the steering loop - when agents repeat a class of mistake, ensure a control is engineered so it cant happen again - and keep repository knowledge (docs, specs, context) legible to agents, fighting drift continuously.
• Track and act on 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.
• Coordinate day-to-day activities and direct team members; monitor performance, and provide coaching, counseling, and motivation to maximise contribution.
• Collaborate with relevant stakeholders to attract talent, set goals, and measure and reward performance.
• Serve as a source of technical expertise, including guidance on the effective and responsible use of AI tools.

What Were Seeking

• Bachelors/Masters in Computer Science or related discipline, or relevant experience in software design, development, and testing.
• Strong software engineering background in large, complex codebases, with genuine care for architecture, testing, and maintainability - you remain hands-on.
• 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 - youd 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.
• Strong people management experience with the proven ability to manage a high-performing team, including navigating the organisational change that AI adoption brings.
• Demonstrated ability to drive AI adoption within a team while governing responsible use, managing associated risks, and maintaining compliance awareness.
• 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.
• Familiarity with CI/CD pipelines, containerization (e.g. Docker, Kubernetes), and infrastructure-as-code as they relate to managing modern engineering teams.
• Excellent communication skills to articulate design, strategy, and standards across teams.