AI Evaluation Engineer

AI Evaluation Engineer ABOUT DISTYL AI Distyl is an applied AI technology company partnering with the world’s most ambitious institutions to rearchitect critical operations for the frontier of AI. Our customers include the largest companies in telecom, healthcare, insurance, manufacturing, consumer goods, and global social organizations. We research and deploy technologies that power AI-native operations — both for our partners and for Distyl itself. Our work spans research into self-constructing systems, the development of the most reliable execution of AI systems, and products that transform mission-critical workflows. As a result, Distyl's technologies affect some of the world's largest operations — from hundreds of millions of consumer interactions to tens of millions of supply chain transactions and millions of patient journeys. Distyl is backed by leading investors including Lightspeed Venture Partners, Khosla Ventures, Coatue, DST Global, and the board-members of 20+ F500s. The results reflect this approach: a 100% production deployment success rate for our customers and one of the few enterprise AI companies to run a profitable business. WHAT WE ARE LOOKING FOR At Distyl, we build AI systems using Evaluation-Driven Development—an approach where evaluation is not an afterthought, but the primary mechanism for iterating, improving, and trusting AI behavior in production. AI Evaluation Engineers focus on designing and implementing the evaluation systems that drive this process. They are hands-on engineers who write production Python code, build evaluation pipelines, and use structured signals to guide system design, prompt iteration, and deployment decisions for real customer-facing AI systems. This role is for engineers who believe that AI systems only improve when measurement is tightly coupled to development—and who want to apply that philosophy directly to systems that matter. KEY RESPONSIBILITIES - Design and implement evaluation frameworks that enable Evaluation-Driven Development for AI systems deployed in customer environments - Define how system quality is measured in each domain, ensuring that evaluation signals reflect real user needs, domain constraints, and business objectives - Build and maintain golden test cases and regression suites in Python, using both human-authored and AI-assisted test generation to capture critical behaviors and edge cases. These test suites are treated as first-class system components that evolve alongside the AI system itself - Develop and maintain evaluation pipelines—offline and online—that integrate directly into system iteration loops. Evaluation results inform prompt design, agent logic, model selection, and release readiness, ensuring that system changes are driven by measurable improvements rather than intuition alone - Define, calibrate, and operate LLM-based graders, aligning automated judgments with expert human assessments. They investigate where evaluation signals diverge from real-world outcomes and refine grading approaches to maintain signal quality as systems and domains evolve - Work closely with Forward Deployed AI Engineers, Architects, Product Engineers, AI Strategists, and domain experts to ensure evaluation frameworks meaningfully guide system development and deployment in production WHAT WE REQUIRE - 2+ years of software engineering experience - Strong Python Engineering Skills: Write clean, maintainable Python and are comfortable building evaluation and experimentation pipelines that run in production environments. You treat evaluation code with the same rigor as application code - Experience with Evaluation-Driven or Experiment-Driven Development: Experience using structured evaluation or experimentation frameworks to drive system iteration, and understand the pitfalls of overfitting to metrics that don’t reflect real outcomes - Ability to Translate Human Judgment into Code: Work with subject matter experts to elicit high-quality judgmen ... (truncated, view full listing at source)