About the job
As the Technical Program Manager for AI Agent Quality and Evaluation, you will be the strategic owner of evaluation infrastructure that ensures AI agents deliver reliable, high-quality outcomes at scale. You will scale evaluation efforts across agent quality (e.g., capability-based evaluations, user feedback pipelines, quality dashboards) and product evaluations (e.g., workflow validation, real-world task completion metrics). You will establish the quality bar for self-sustaining agent execution across software development, operations, and enterprise workflows. In this role, you will own the evaluation strategy for AI agent programs. You will work at the intersection of research, engineering, and product to ensure our AI agents meet the highest quality standards before deployment.
Responsibilities
Develop and scale capability-based evaluation frameworks for AI agents.
Establish quality dashboards and leaderboards for tracking agent performance and latency.
Guide user feedback pipelines to collect and curate high-quality evaluation examples.
Co-ordinate benchmark evaluations comparing agent capabilities against baselines.
Collaborate with evaluation teams to validate agent capabilities across various use cases.
Qualifications
Minimum
Bachelor's degree or equivalent practical experience.
10 years of experience in program or project management.
10 years of experience managing cross-functional or cross-team projects.
Preferred
Experience building and scaling evaluation infrastructure for AI/ML systems, including benchmark design, metrics definition, and quality tracking.
Experience partnering with research and engineering teams in fast-paced environments to guide program delivery from concept to completion.
Understanding of the unique challenges in evaluating agentic behavior with a passion for AI agents and self-sustaining systems.
Ability to prioritize, adapt to change, and provide flexible thought partnership in an evolving landscape.
Excellent communication skills with the ability to develop meaningful relationships with key partners and influence action and outcomes.