Principal Harness Engineer

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

📋 Description

• Design, develop, deploy, and maintain core harness elements, which include guides, feedback loops, guardrails, and shared context.

• Take ownership and enhance feedforward guides, agent instruction files, reusable skills, architectural guidelines, reference documentation, and codemods.

• Drive standardization across the team to ensure agents generate accurate output on the initial attempt.

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

• Manage quality gating and establish release criteria for work produced by agents.

• Define authority boundaries for unaided agent merges and set escalation protocols for human review.

• Develop LLM testing infrastructure and evaluation methodologies for AI-generated outputs.

• Implement consumer/contract testing in scenarios where service integration reliability is crucial.

• Operate the steering loop and uphold repository knowledge as the definitive source of information.

• Determine the placement of controls in the production pathway.

• Enhance visibility into agent tasks and monitor engineering and agent-PR metrics.

• Collaborate with product and platform teams to translate specifications and acceptance criteria into enforceable controls.

• Act as a technical expert and mentor to engineers across teams in harness practices and responsible AI tool usage.

⛳️ Requirements

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

• Experienced software engineer with a background in large, intricate codebases and a solid foundation in architecture and design.

• Practical experience with AI coding agents (e.g., Claude Code, Codex, or similar technologies).

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

• Familiarity with agent instruction conventions such as AGENTS.md.

• Knowledge of spec-driven development, context engineering, agent orchestration, fitness functions, and developer-platform integration.

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

• Sound judgment regarding deterministic computational controls compared to inferential LLM-based controls, considering trade-offs in cost, speed, and reliability.

• Experience in managing quality-gating processes and defining release criteria.

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

• Familiarity with consumer/contract testing methodologies such as Pact.

• Strong communication skills with the ability to articulate design concepts to architects and promote standards across teams.

🏝️ Benefits

• Highly competitive compensation, benefits, and rewards programs.

• Emphasis on work/life balance.

• Employee resource groups.

• Social events.

• Opportunities for learning experiences and professional development.

• An inclusive, people-first work environment.