Reinforcement Learning Engineer, Policy, Digital Optimus

What You'll Do

• Lead large-scale post-training runs using PPO, GRPO, and related methods on agent trajectories
• Design and build evaluation systems, benchmarks, and scorers to diagnose and fix policy issues in long-horizon tasks
• Create reward signals and feedback loops combining outcomes, process supervision, safety, and human feedback
• Run and optimize distributed RL training pipelines at scale
• Iterate quickly on training data, reward shaping, and multimodal policies
• Collaborate with Harness, Vision, and Infrastructure teams to deploy improved policies

What You'll Bring

• Strong hands-on experience with RL post-training for LLMs/VLMs (PPO, GRPO, RLHF, or similar)
• Experience building evaluation frameworks and turning insights into training improvements
• Proficiency with distributed training systems (DeepSpeed, FSDP, Ray) and large-scale data pipelines
• Solid software engineering skills (Python) and intuition for production ML systems
• Understanding of long-horizon RL challenges: credit assignment, reward hacking, and training stability
• Background in computer-use agents, robotics RL, or screen/GUI interaction is a plus
• Experience with large-scale RL on real user data is a plus
• Contributions to RLHF, RLAIF, or GRPO implementations is a plus

Benefits

• Competitive pay
• Medical plans
• Fertility, adoption, and surrogacy benefits
• Dental and vision plans
• HSA Contribution
• Flexible Spending Accounts (FSA)
• 401(k) with employer match
• Employee Stock Purchase Plans
• Other financial benefits
• Basic Life, AD&D, Short-term and long-term disability insurance
• Employee Assistance Program
• Sick and Vacation time
• Paid Holidays
• Back-up childcare and parenting support resources
• Voluntary benefits
• Weight Loss and Tobacco Cessation Programs
• Tesla Babies program
• Commuter benefits
• Employee discounts and perks program

Expected Compensation

$124,000 - $558,000/annual salary + cash and stock awards + benefits