Senior Research Engineer for Reinforcement Learning

Job Description

NVIDIA is seeking a senior or principal engineer specializing in large-scale reinforcement learning and policy learning for humanoid robots in the GEAR group.

Requirements

• Bachelor’s degree or above in Computer Science, Robotics, Engineering, or a related field
• 5+ years of industry experience on large-scale deep learning or MLOps
• Exceptional engineering skills in building, testing, and maintaining scalable distributed GPU training frameworks
• Proficiency in Python
• Hands-on model training experience in PyTorch, JAX, or Tensorflow
• Deep familiarity with reinforcement learning algorithms like PPO, SAC, or Q-learning
• Familiarity with common policy learning techniques like reward shaping, domain randomization, curriculum learning
• Strong experience with large-scale GPU clusters, HPC environments, and job scheduling/orchestration tools (e.g., SLURM, Kubernetes)

Responsibilities

• Develop a large-scale reinforcement learning training framework capable of running on thousands of GPUs
• Build and optimize simulation infrastructure to support the training of locomotion and manipulation policies for robots at scale
• Develop sim-to-real transfer pipelines and work closely with the robotics team to deploy to physical robots
• Propose scalable solutions that combine LLMs with policy learning
• Apply reinforcement learning to finetune multimodal LLMs

Benefits

• Multiple relocation packages
• Two weeklong shutdowns (mid-summer and year-end) in the US (in addition to PTO)
• 8-week parental leave
• 9 Employee Resource Groups
• Annual bonus offering
• Flexible work arrangements
• Up to 6% 401K matching