Gemini Post-Training AI Engineer — Reinforcement Learning

Google; United States; On-site; USD 174,000 - 252,000; Full time

Job summary

The Gemini post-training software engineer role at Google DeepMind invites you to help advance AI agents from research to production. You will design, train, and evaluate models used in diverse digital environments, focusing on reliability, scalability, and safety across large-scale systems.

Position offers location options in Mountain View, CA and New York, NY, with equity and a 15% bonus target. Google emphasizes equal opportunity and global collaboration, and expects strong Python skills, ML

Qualifications

• Bachelor's degree in CS or equivalent practical experience.
• 5 years of experience designing, training, and evaluating ML models.
• Experience in Python programming.
• Experience in ML testing for post-silicon data collection, and pre-silicon modeling and correlation.
• Experience with Large Language Models, NLP, or Generative AI.

Responsibilities

• Make core contributions to Gemini that advance what digital agents can do and are deployable into production.
• Identify model areas of improvement.
• Train and evaluate agents across various digital environments.
• Focus on multi-step reinforcement learning in multimodal, digital environments.

Skills

Python programming

ML experience

ML testing

LLMs NLP Generative AI

Model training evaluation

Education

Bachelor's degree in Computer Science or equivalent

Job description

The Gemini post-training software engineer role at Google DeepMind invites you to help advance AI agents from research to production. You will design, train, and evaluate models used in diverse digital environments, focusing on reliability, scalability, and safety across large-scale systems.

Position offers location options in Mountain View, CA and New York, NY, with equity and a 15% bonus target. Google emphasizes equal opportunity and global collaboration, and expects strong Python skills, ML