Senior Product Manager, Eval Quality, AI Data

Artificial Intelligence is evolving at an unprecedented pace, and AI Agents represent the next frontier. These agents, capable of complex reasoning, tool use, and interacting with dynamic environments, are poised to redefine how we live and work. Ensuring these agents are safe, reliable, and effective is paramount, and that's where evaluations come in.

Evaluations have always been the bedrock of successful AI development. However, the methods used for traditional Large Language Models fall short when it comes to agents. Unlike static models, agents operate in a world of vast possibilities, delivering value through a sequence of actions and interactions.

We need to pioneer new ways of thinking for agent evaluation. Think Waymo online: we must create rich, dynamic simulation environments to test agents against a massive state space, uncovering failure modes and ensuring robust performance across countless scenarios. This isn't just an incremental improvement; it's about defining how the next generation of AI will be validated.

If you're passionate about pushing the boundaries of AI and solving some of the most problems in the field, this is your chance. Come join our Evals team, where with products like Everest and EvalHub, we empower GenAI model development across Google. In this role, you will lead the product goal for how Google evaluates AI Agents, ensuring we build the most capable and trustworthy agentic systems in the world.

• Develop a first-principles understanding of what makes an evaluation task truly useful-optimizing for coverage, climbability (scaling with compute and data while preserving headroom), discriminability, statistical stability (tight confidence intervals), and zero contamination.
• Synthesize insights into a holistic product goal and roadmap for Eval Quality.
• Operate seamlessly across Product Area boundaries between Gemini, AI2, and other partner product areas.
• Grow in Gemini's dynamic, fast-moving, research-driven environment where priorities evolve rapidly and Product Managers earn trust by directly contributing to day-to-day execution.