Staff Research Scientist: LLMs, Post-Training & RL

Google LLC; San Francisco (CA); Hybrid; USD 207,000 - 300,000; Full time

Benefits offered by this job

Health insurance

Dental insurance

Vision insurance

Life insurance

Disability insurance

401(k) match

Paid time off

Sick leave

Maternity leave

Baby bonding leave

Holidays

Job summary

Google DeepMind is seeking a Staff Research Scientist/Engineer focused on agentic post-training with deep learning, LLMs, and reinforcement learning. You will drive experiments, design ablation studies, and communicate outcomes to cross-functional teams while advancing Gemini model work.

The role emphasizes core modeling over ML infra, with global AI safety and ethics underpinning our research direction. Applicants should have extensive experience and leadership in complex projects.

Qualifications

• Bachelor’s degree or equivalent practical experience.
• 8 years of experience in software development.
• 5 years of experience testing and launching software products.
• 3 years of experience with software design and architecture.
• Experience with large language model, reinforcement learning, and deep learning.

Responsibilities

• Specialize in core modeling and post-training experience for agent research.
• Drive research process for large-scale agent post-training in Gemini model recipe.
• Design and execute ablation studies to validate hypotheses.
• Communicate findings through visualizations and reports.
• Collaborate with researchers and engineers to maintain feedback loops.

Skills

8+ years software development

5 years testing

3 years design/architecture

Large language models (LLMs)

Reinforcement learning

Deep learning

Education

Bachelor’s degree or equivalent practical experience

Master’s degree or PhD in Engineering/CS or related

Job description

Google DeepMind is seeking a Staff Research Scientist/Engineer focused on agentic post-training with deep learning, LLMs, and reinforcement learning. You will drive experiments, design ablation studies, and communicate outcomes to cross-functional teams while advancing Gemini model work.

The role emphasizes core modeling over ML infra, with global AI safety and ethics underpinning our research direction. Applicants should have extensive experience and leadership in complex projects.