# Jobgether — Director/Senior Manager - AI Harness Engineering ## Posting metadata - Canonical JD URL: https://www.linkedin.com/jobs/view/4452431170 - Provider: LinkedIn public job posting - Location/source location: United States - Work model: Remote, United States - Compensation: $150,500-$236,500 base - Travel: Not disclosed - Posted: Unavailable - LinkedIn relative posting time at capture: 5 days ago - Applicants: Be among the first 25 applicants - Generated: 2026-08-16 10:23 AM EDT - Elapsed since posting: Unavailable ## Fit decision - Positioning track: Technical manager - Central mandate: Establish an enterprise engineering harness that governs, tests, secures, measures, and continuously improves autonomous coding-agent output. - Fit outcome: BORDERLINE - Weighted fit score: 73.3% - Keyword diagnostic: Not applicable because no resume was generated. - Validation: Fit gate complete; no application package generated. ## Hard and material gaps - Keith has recent Codex, agentic-coding, AGENTS.md, OpenClaw-skill, governance, CI/CD, and observability experience, but not direct evidence of owning an enterprise-scale AI coding-agent harness discipline. - Custom linters, architecture-fitness tests, cost-per-merged-PR metrics, prompt-injection controls, and LLM testing infrastructure are adjacent rather than directly evidenced at the required scope. ## Evidence map | Requirement | Weight | Evidence score | Keith evidence | |---|---:|---:|---| | Hands-on AI coding agents such as Codex or Claude Code | 3 | 2/3 | Direct recent Codex and agentic-coding experience, but limited enterprise-duration evidence. | | Engineering tooling, linters, structural tests, CI/CD, and containers | 3 | 2/3 | Strong CI/CD, testing, Docker, code review, and delivery; custom linters/fitness tests are less direct. | | AGENTS.md, reusable skills, context engineering, and orchestration | 2 | 3/3 | Direct OpenClaw skill development, agent instructions, orchestration, and multi-agent experience. | | AI governance, LLM tests, quality gates, and durable controls | 2 | 2/3 | Direct governance and quality-control evidence; coding-agent-specific LLM test infrastructure is adjacent. | | Prompt injection, sandboxing, least privilege, and agent security | 2 | 1/3 | IAM, auditability, privacy, and secure cloud experience; explicit coding-agent security controls are less direct. | | Lead geographically distributed engineers | 2 | 3/3 | Led distributed teams and global technical communities. | | Remain hands-on while setting technical direction | 2 | 3/3 | Repeated founder, VP, Director, and architect player-coach roles. | | AI engineering metrics such as cost and PR survival | 1 | 1/3 | KPI and AI-cost experience exists, but the named measures are not directly evidenced. | | Spec-driven development, fitness functions, and developer platforms | 2 | 2/3 | Requirements-to-architecture, testing, platform, and automation evidence is direct; fitness-function ownership is adjacent. | | Remote engineering leadership | 1 | 3/3 | Extensive remote and distributed leadership. | ## Artifact metadata - Resume: Not generated - Cover letter: Not generated ## Full normalized job description This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Director/Senior Manager - AI Harness Engineering based in the United States. As a Director/Senior Manager of AI Harness Engineering, you will establish and lead a new engineering discipline focused on making AI coding agents reliable at enterprise scale. You will design the systems, controls, feedback loops, and shared context that help autonomous agents consistently produce production-grade software. This is a hands-on leadership role where you will contribute code while setting technical direction, quality standards, and governance practices. You will lead a geographically distributed team and collaborate closely with engineering, product, security, and platform stakeholders. Your work will help shift software quality from manual review toward enforceable, observable, and repeatable engineering systems. You will shape how AI-assisted development is governed, measured, secured, and adopted across complex engineering organizations. This is an opportunity to define an emerging discipline while directly influencing the future of software engineering and AI-enabled development. Accountabilities Design, build, and continuously evolve an AI engineering harness consisting of agent guidance, feedback loops, guardrails, shared context, and quality controls that turn AI model capabilities into reliable production engineering. Develop and maintain feedforward guidance such as agent instruction files, reusable skills, architectural rules, reference documentation, and codemods, driving consistent adoption across engineering teams. Build automated feedback mechanisms including custom linters, structural tests, architecture-fitness tests, verification loops, and LLM-based reviewers to identify issues before human review. Establish and own regional AI governance, including authority boundaries for autonomous agent actions, LLM testing infrastructure, and quality, security, and compliance thresholds for AI-generated software. Define cross-organizational QA and quality-gating standards that create consistent and enforceable engineering practices across teams and product areas. Operate continuous improvement loops that identify recurring agent errors and turn those failure patterns into durable controls, while maintaining repository documentation and context as a trusted system of record. Determine where controls should operate throughout the software delivery lifecycle, balancing fast pre-commit checks, deeper post-integration validation, and continuous monitoring for architectural or quality drift. Establish observability for AI-assisted engineering and track meaningful metrics such as cost per merged pull request, time to merge, review velocity, defect escape rate, and agent-generated PR survival rate. Lead, coach, and grow a geographically distributed team of harness engineers, including talent development, performance management, goal setting, and organizational growth. Partner with engineering and product leadership to translate specifications and acceptance criteria into enforceable technical controls and align harness capabilities with platform and delivery roadmaps. Drive internal enablement through presentations, technical guidance, knowledge sharing, and thought leadership on agent-augmented software engineering. Balance deterministic engineering controls such as type checkers, linters, and structural tests with inferential AI-based controls such as automated code review and LLM-as-judge systems. Establish secure operating boundaries for autonomous agents, including least-privilege permissions, sandboxed execution, tool access controls, auditability, and protections against prompt injection. Requirements Strong software engineering background with experience working in large, complex codebases and a demonstrated commitment to architecture, testing, maintainability, and engineering quality. Hands-on experience using AI coding agents such as Claude Code, Codex, or comparable technologies, with a strong understanding of their capabilities, limitations, and common failure modes. Experience building engineering tooling across modern development environments, including linters, static analysis, CI/CD pipelines, containerized build and test environments, instrumentation, and observability. Familiarity with agent instruction conventions such as AGENTS.md and with emerging practices in context engineering and agent orchestration. Experience with spec-driven development, fitness functions, developer platforms, and systems designed to enforce engineering quality mechanically and consistently. Strong systems-thinking mindset, with the ability to improve the environment and underlying controls rather than repeatedly fixing individual outputs. Sound judgment when selecting deterministic computational controls versus probabilistic or inferential LLM-based controls, including an understanding of their respective cost, speed, reliability, and maintenance trade-offs. Demonstrated experience establishing AI governance, enterprise quality standards, LLM testing infrastructure, and quality gates for AI-generated artifacts. Working knowledge of security risks associated with autonomous AI agents, including prompt injection, tool and permission scoping, sandboxing, least-privilege design, and audit trails. Significant experience managing geographically distributed, high-performing engineering teams, including leading organizational change associated with AI adoption. Excellent communication and stakeholder management skills, with the ability to articulate technical strategy, design principles, governance requirements, and quality standards across diverse teams. Bachelor's or Master's degree in Computer Science or a related discipline, or equivalent professional experience in software architecture, development, design, and testing. Ability to remain hands-on while providing strategic leadership, setting technical direction, and establishing a high quality bar for AI-assisted engineering. Benefits Targeted base salary range of $150,500–$236,500, with compensation determined according to relevant knowledge, skills, experience, and other applicable factors. Comprehensive compensation, benefits, and rewards programs designed to recognize strong performance and contribution. Remote work opportunity for U.S.-based employees. People-first culture emphasizing ownership, customer focus, respect, collaboration, and professional excellence. Opportunities to shape an emerging engineering discipline and influence enterprise-wide adoption of AI-assisted software development. Professional development and learning opportunities designed to support continued career growth. Employee resource groups and social programs that encourage connection, inclusion, and collaboration. Work/life balance initiatives and an environment designed to support sustainable performance. Opportunity to work at the forefront of AI, software engineering, analytics, automation, governance, and developer productivity. Meaningful leadership scope, including building and growing a specialized engineering team and defining standards used across the organization. How Jobgether Works We use an AI-powered matching process to ensure your application is reviewed quickly, objectively, and fairly against the role's core requirements. Our system identifies the top-fitting candidates, and this shortlist is then shared directly with the hiring company. The final decision and next steps (interviews, assessments) are managed by their internal team. We appreciate your interest and wish you the best! Why Apply Through Jobgether? Data Privacy Notice: By submitting your application, you acknowledge that Jobgether will process your personal data to evaluate your candidacy and share relevant information with the hiring employer. This processing is based on legitimate interest and pre-contractual measures under applicable data protection laws (including GDPR). You may exercise your rights (access, rectification, erasure, objection) at any time. We may use artificial intelligence (AI) tools to support parts of the hiring process, such as reviewing applications, analyzing resumes, or assessing responses and identifying potential inconsistencies or verification signals in application materials based on available information. These tools assist our recruitment team but do not replace human judgment. Final hiring decisions are ultimately made by humans. If you would like more information about how your data is processed, please contact us.