Senior Harness Engineer

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

📋 Description

• Design, develop, deploy, and maintain essential harness components, including guides, feedback mechanisms, guardrails, and shared context.

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

• Lead team-wide standardization efforts for AI-agent outputs.

• Create feedback sensors 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 and escalation protocols for agent actions.

• Set up LLM testing infrastructure and evaluation methodologies.

• Implement consumer/contract testing to ensure service integration reliability.

• Oversee the steering loop to avoid recurring agent errors.

• Preserve repository knowledge and mitigate documentation drift.

• Determine where controls are implemented throughout the production pathway.

• Enhance observability into agent operations and monitor engineering metrics.

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

• Mentor engineers across various teams in harness practices and responsible use of AI tools.

⛳️ Requirements

• Bachelor’s or Master’s degree in Computer Science or related fields, 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).

• Proven track record in developing engineering tools across a modern technology stack, including linters, static analysis, CI/CD pipelines, containerized build/test environments, and instrumentation/observability.

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

• Experience with specification-driven development, context engineering, agent orchestration, fitness functions, and developer-platform collaboration.

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

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

• Experience in overseeing quality-gating processes and establishing release criteria.

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

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

• Exceptional communication skills; capable of articulating designs with architects and promoting standards across teams.

🏝️ Benefits

• An inclusive culture that embodies FICO’s core values.

• Opportunities for professional development and valuable learning experiences.

• Competitive compensation along with benefits and rewards programs.

• Emphasis on work/life balance.

• Access to employee resource groups.

• Social events that foster interaction and camaraderie.