Research Scientist, Agent Post-Training

Job Description

At Google DeepMind, we've built a unique culture and work environment where long-term ambitious research can flourish. In this role, you will push the frontier of agentic tasks in post-training large language models as a Research Scientist or Research Engineer (we are open to both). As part of the Gemini post-training team, you will have the chance to drive the research that makes up the backbone of upcoming releases. You will help bridge research and engineering by designing scalable experiments and building reliable infrastructure for tool use and reinforcement learning. You will value various experience and backgrounds to create extraordinary impact. Artificial intelligence will be one of humanity’s most transformative inventions. At Google DeepMind, we are a pioneering AI lab with exceptional interdisciplinary teams focused on advancing AI development to solve complex global challenges and accelerate high-quality product innovation for billions of users. We use our technologies for widespread public benefit and scientific discovery, ensuring safety and ethics are always our highest priority. We are pushing the boundaries across multiple domains. Our global teams offer various learning opportunities and varied career pathways for those driven to achieve exceptional results through collective effort. Responsibilities Lead the full research process, from forming hypotheses to delivering direct impact in Gemini post-training. Design effective ablations to systematically validate and iterate on research ideas. Communicate research findings and experimental results through clear plots and reports. Develop reliable infrastructure and utilities to support post-training research and evaluations. Collaborate with other researchers and engineers to accelerate project velocity.

Skills Required

• reinforcement learning (RL)
• supervised fine-tuning (SFT)
• agent-based systems
• JAX
• Flax
• TensorFlow
• PyTorch
• systems design