Cyber Gemini Research Engineer - Post-Training & RL Safety

DeepMind Technologies Limited; New York (NY); On-site; USD 147,000 - 210,000; Full time

Benefits offered by this job

Bonus target

Equity

Benefits

Job summary

DeepMind Technologies Limited is hiring a Research Engineer in the Cyber Gemini team to advance scalable research infrastructures for vulnerability discovery and evaluation. You will work on RB environments, post-training recipes, and agent evaluation pipelines across large-scale AI safety projects in collaboration with Google and academia.

The role emphasizes building datasets, iterating on training recipes, and integrating cybersecurity models into scalable systems while contributing to the

Qualifications

• PhD in Computer Science or a related field, or equivalent practical experience.
• 2 years of experience (industry or academia) working in Reinforcement Learning environments.
• Experience building distributed system infrastructure.
• One or more publication records in vulnerability research (e.g. auditing, reverse engineering, exploitation).

Responsibilities

• Build datasets (RL environments, SFT data) and iterate on post-training recipes.
• Debug and analyze RL training runs to identify bottlenecks and optimize training efficiency.
• Build evaluation pipelines, benchmarks, and leaderboards to measure agent performance.

Skills

Reinforcement Learning

Distributed systems

Publication records in vulnerability

Education

PhD in Computer Science or related field

Job description

DeepMind Technologies Limited is hiring a Research Engineer in the Cyber Gemini team to advance scalable research infrastructures for vulnerability discovery and evaluation. You will work on RB environments, post-training recipes, and agent evaluation pipelines across large-scale AI safety projects in collaboration with Google and academia.

The role emphasizes building datasets, iterating on training recipes, and integrating cybersecurity models into scalable systems while contributing to the