Director – Senior Manager, AI Harness Engineering

This is a fully remote position, open to applicants in United States.

📋 Description

• Design, construct, and enhance the AI framework that includes guides, feedback loops, guardrails, and shared context.

• Contribute to production code by developing feedforward guides, reusable skills, architectural guidelines, reference documents, and codemods.

• Create feedback mechanisms such as custom linters, architecture fitness tests, verification loops, and LLM-as-judge reviewers.

• Oversee regional AI governance, agent authority boundaries, LLM testing infrastructure, and ensure quality, safety, and compliance thresholds.

• Define and manage cross-organizational QA and quality-gating standards.

• Operate the steering loop to mitigate recurring agent errors and continuously oversee repository knowledge and drift.

• Determine the placement of controls across pre-commit, post-integration, and continuous monitoring phases.

• Establish observability into agent operations and take responsibility for engineering performance metrics.

• Manage, mentor, and develop a geographically distributed team of harness engineers.

• Collaborate with engineering leaders and product management to translate specifications and acceptance criteria into actionable controls.

• Provide internal enablement, deliver presentations, and demonstrate thought leadership in agent-augmented engineering.

⛳️ Requirements

• Strong background in software engineering with experience in large, complex codebases.

• Practical experience with AI coding agents such as Claude Code, Codex, or similar technologies.

• Experience in developing engineering tools across linters, static analysis, CI/CD pipelines, containerized build/test environments, and instrumentation/observability.

• Familiarity with agent instruction conventions, including AGENTS.md.

• Experience in spec-driven development, context engineering, agent orchestration, fitness functions, and developer-platform initiatives.

• Capability to encode engineering quality into systematic, repeatable rules.

• Discernment regarding deterministic computational controls versus inferential LLM-based controls, and understanding of their cost, speed, and reliability trade-offs.

• Proven experience in managing AI governance and establishing cross-organizational quality standards, including LLM testing infrastructure and quality gating for AI-generated outputs.

• Working knowledge of autonomous-agent security, encompassing prompt injection, tool/permission scoping, sandboxed execution, and audit trails.

• Strong experience in managing high-performing, geographically distributed engineering teams.

• Excellent communication abilities.

• Bachelor’s/Master’s degree in Computer Science or a related field, or equivalent experience in software architecture, design, development, and testing.

🏝️ Benefits

• Highly competitive compensation, benefits, and rewards programs.

• Work/life balance.

• Employee resource groups.

• Social events to foster interaction and camaraderie.

• Opportunities for professional development through valuable learning experiences.

• Inclusive, people-first work environment.

• Equal employment and advancement opportunities.