Senior AI Safety and Alignment Research Scientist

Google DeepMind; Mountain View (CA); On-site; USD 207,000 - 300,000; Full time

Job summary

Google DeepMind's Gemini Safety team is accountable for the standards of GDM’s flagship releases. In this role, you will develop algorithmic solutions to advance user-facing architectures. The workstyle is changing, supported by a strong internal culture of mutual dedication and cooperation.

You will bring a Large Language Model (LLM) post-training expertise to ensure outputs are aligned and production-ready. You will be a builder and shipper who takes end-to-end ownership.

Qualifications

• PhD in Computer Science, a related field, or equivalent practical experience.
• 3 years of experience initiating, scoping, and executing research agendas or leading academic projects.
• One or more peer-reviewed scientific publication submissions (e.g., NeurIPS, ICML, ICLR, CVPR, ACL, CoRL) or public preprint repositories (arXiv).

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 issues 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

PhD level research leadership

Three years research program exposure

Publications in AI/ML venues

Education

PhD in Computer Science or related field

Job description

Google DeepMind's Gemini Safety team is accountable for the standards of GDM’s flagship releases. In this role, you will develop algorithmic solutions to advance user-facing architectures. The workstyle is changing, supported by a strong internal culture of mutual dedication and cooperation.

You will bring a Large Language Model (LLM) post-training expertise to ensure outputs are aligned and production-ready. You will be a builder and shipper who takes end-to-end ownership.