Principal Engineer – Agentic Development

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

📋 Description

• Collaborate with Product teams to transform early-stage ideas into structured Proofs of Concept, determining technical feasibility and scope.

• Create comprehensive specifications and acceptance criteria for coding agents.

• Oversee the code generated by agents throughout the deployment process.

• Implement stringent quality standards for agent-generated output in a regulated decision-making environment.

• Operate within the agentic framework using guides, AGENTS.md files, architectural guidelines, reference documentation, linters, fitness tests, verification loops, and LLM-as-judge reviewers.

• Diagnose the root causes of recurring agent errors and establish systemic controls in collaboration with the harness team.

• Ensure precise repository documentation, specifications, and contextual knowledge are maintained.

• Utilize technical judgment concerning architecture, edge cases, latency, integration risks, auditability, and agent autonomy.

⛳️ Requirements

• Proven experience in software engineering within extensive, complex codebases.

• Solid foundation in software architecture, testing methodologies, and long-term maintainability.

• Hands-on experience working with AI coding agents such as Claude Code, GitHub Copilot, Codex, or Cursor.

• Understanding of AI coding agents’ capabilities, limitations, and suitable applications in production engineering workflows.

• Capacity to critically assess agent-generated output and pinpoint subtle errors or architectural flaws.

• Proficiency in producing clear, unambiguous, testable, and actionable technical specifications and definitions of done.

• Methodical approach to verification, checks, and test coverage.

• Results-driven accountability for the quality and accuracy of delivered work.

• Familiarity with Python, SQL, JavaScript/TypeScript, AWS or Azure, Kubernetes, CI/CD pipelines, ML model deployment, or real-time decision-making systems.

• Experience in spec-driven development, context engineering, or agent orchestration is a significant asset.

• Knowledge of regulated or audited software delivery processes and controlled change management is a plus.

• Background in decision-making, credit risk, fraud detection, analytics, optimization, or data engineering is beneficial.

• Ability to articulate a well-thought-out approach to human-AI collaboration, delegation boundaries, human oversight, and earning autonomy through demonstrated quality.

🏝️ Benefits

• Highly competitive compensation, benefits, and rewards programs.

• Work/life balance.

• Employee resource groups.

• Social events.

• Learning experiences and opportunities for professional development.

• Inclusive, people-first work environment.