Director/Senior Manager - AI Harness Engineering

The Opportunity

As a Director, AI Harness Engineering, you will build and lead a new 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), and we're building a dedicated Harness Engineering team to own it. This is a hands-on leadership role: you will design and build harness components while leading and growing a regional team of harness engineers and setting the quality bar for AI-assisted engineering across the organization.

What You'll Contribute

• Design, build, and evolve 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) that help agents get it right the first time 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 automatically before they reach human reviewers.

• Own AI governance for your region: define authority boundaries for what agents may merge unaided, establish LLM testing infrastructure, and ensure AI-generated output meets quality, safety, and compliance thresholds before release.

• Define and own cross-organizational QA and quality-gating standards, ensuring consistent, enforceable engineering practices across teams and product areas.

• Run the steering loop at scale — when agents repeat a class of mistake, ensure a control is engineered so it cannot happen again — and treat repository knowledge (docs, specs, context) as the system of record, fighting drift continuously.

• 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.

• Establish observability into agent work and own 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 direct where the team invests next.

• 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 closely with other engineering leaders and product management to turn specifications and acceptance criteria into enforceable controls, and to align the harness with platform and delivery roadmaps.

• Demonstrate expertise through internal enablement, presentations, and thought leadership on agent-augmented engineering.

What We're Seeking

• Strong software engineering background with experience in large, complex codebases, and genuine care for archi