Software Engineering Director, Agentic Evaluations (Fully Remote)

• Lead the development of credible, repeatable evaluations for live AI agents.
• Own the technology stack supporting the evaluation platform, from APIs to orchestration.

Key Responsibilities:

• Design reusable evaluation primitives applicable across software categories.
• Partner with data science teams to develop proprietary benchmarks.
• Promote the effective use of evaluations across agent-focused products.

Requirements:

• 10+ years of backend or full-stack development experience.
• 2+ years of engineering management experience.
• Hands-on experience evaluating AI agents and using frontier models.
• Total earnings of approximately $260,000-$320,000.
• Unlimited PTO, equity, and comprehensive parental leave.

Partner Company

This company focuses on building credible, scalable evaluations of AI agents from software vendors. It operates as a fully remote, inclusive team with a flexible culture and a focus on professional growth.