AI Safety & Alignment Research Scientist

DeepMind Technologies Limited; Mountain View (CA); On-site; USD 174,000 - 252,000; Full time

Job summary

Google DeepMind seeks a Research Scientist for the Gemini Safety team to design algorithmic solutions advancing user-facing architectures. You will bring post-training expertise to ensure outputs are aligned and production-ready, coordinating with Gemini post-training and core Product Area counterparts.

You will be a builder and shipper with end-to-end ownership, formulating mitigation frameworks and evaluations while guiding cross-functional alignment for deployment across launch surfaces.

Qualifications

• PhD in Computer Science, a related field, or equivalent practical experience.
• 1 year experience with Generative AI, Large Language Models, natural language processing, or Agent-based systems.

Responsibilities

• Design, implement, and maintain high-quality protocols to identify safety gaps in model behavior across all Gemini and GenAI models, and feed these insights back into the post-training process to continuously improve both in-model and out-of-model protection.
• Explore, adapt, and apply innovative modeling and alignment techniques to solve real-world safety and alignment challenges under tight launch timelines.
• Drive innovation in model optimization, advancing the application of Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) techniques at massive scale.
• Partner closely with post-training, evaluation, and product teams to align incentives, close safety gaps, and influence safety decisions without direct authority.

Skills

Generative AI experience

Education

PhD in Computer Science or related field

Job description

Google DeepMind seeks a Research Scientist for the Gemini Safety team to design algorithmic solutions advancing user-facing architectures. You will bring post-training expertise to ensure outputs are aligned and production-ready, coordinating with Gemini post-training and core Product Area counterparts.

You will be a builder and shipper with end-to-end ownership, formulating mitigation frameworks and evaluations while guiding cross-functional alignment for deployment across launch surfaces.