Domain Applied ML (DAML) operates as Google’s "Applied AI Layer," architecting the technical bridge between Google DeepMind’s frontier research and massive-scale product deployment. We define the company-wide strategy for Foundation Model adoption and engineer high-performance solutions in critical domains. In this role, you will pioneer the next generation of Agentic Reinforcement Learning. You will architect the "cognitive" layer of Google’s AI stack—developing novel RL recipes, reward modeling systems, and synthetic data flywheels that enable models to reason, plan, and use tools effectively. You will translate frontier research into scalable production infrastructure, solving the "GenAI Engineering Gap" by transforming probabilistic models into reliable, self-improving agentic systems.

Architect and implement advanced Reinforcement Learning (RL) workflows for complex, multi-turn agentic tasks.

Develop novel training recipes for reasoning, self-correction, and tool use (e.g., CoT, Tree of Thoughts) to improve model reliability in long-horizon workflows.

Design robust reward systems and simulation environments ("Digital Twins") to evaluate and train agents.

Create the "Intelligence Assets" required to train specialized student models, bridging the gap between generalist teacher models and domain-specific production requirements.

Contribute to the unified middleware layer that democratizes access to state-of-the-art tuning.

Implement efficient adaptation techniques (e.g., LoRA, Distillation, Quantization) to ensure high-performance agents can be deployed under strict latency and cost constraints.

Partner with Google DeepMind researchers to validate novel algorithmic approaches (e.g., outcome-supervised vs. process-supervised RMs) and scale them from 0-to-1 prototypes into 1-to-N production libraries used across Google.