Applied Robot Learning Engineer / RL Specialist

About the Role

We are looking for an experienced applied robotics/robot learning engineer with strong reinforcement learning expertise and hands-on experience deploying learning-based policies for complex manufacturing tasks. The role primarily focuses on improving the performance of VLA/world models, addressing sim-to-real challenges, and developing robust and scalable policies for manipulation, failure recovery, and optimal execution. This is a hands-on role requiring real-world deployment experience, comfort working directly with robotic hardware, and flexibility to support broader engineering and experimental tasks as project priorities evolve. The ideal candidate combines strong RL fundamentals with practical robotics engineering experience and some exposure to bimanual manipulation. Approximately 80% of the role will focus on applied engineering, policy implementation, robot experiments, evaluation, and deployment, with 20% dedicated to research and technical exploration. The emphasis is on translating RL methods into measurable improvements on physical robots rather than pursuing research in isolation.

Key Responsibilities

• Develop, fine-tune, and evaluate VLA models and learning-based policies on physical robotic systems.
• Apply reinforcement learning to improve manipulation success rates, execution efficiency, robustness, and recovery from failures.
• Implement and evaluate appropriate approaches such as PPO, SAC, residual RL, policy adaptation, or learned recovery policies.
• Design reward functions and success detectors, including learned or VLM-based reward models, for real-world manipulation tasks.
• Apply sample-efficient methods for real-world training, such as RL from demonstrations, offline-to-online RL, and human-in-the-loop corrections.
• Set up safe real-robot RL, including action limits, workspace constraints, automated resets, and supervised exploration.
• Diagnose sim-to-real gaps and improve real-world performance using techniques such as domain randomization, system identification, and real-world fine-tuning.
• Apply learned policies to manipulation tasks, including tasks involving bimanual setups and coordinated robot execution.
• Design evaluations, analyze failure modes, and measure improvements in success rate, cycle time, generalization, and repeatability.
• Work directly with robotic hardware to run experiments, debug policies, and validate improvements.
• Supervise data collection, identify data-quality issues, and coordinate corrections to demonstrations or datasets.
• Collaborate with the simulation team and contribute to benchmarking, model evaluation, and other hands-on engineering tasks as needed.

Requirements & Tech Stack

• Experience with Git, Python, PyTorch, and ROS/ROS 2.
• Hands-on familiarity with edge compute platforms (NVIDIA Jetson).
• Experience with robotics MLOps ecosystems (experiment tracking, dataset versioning, and visualization tools like Foxglove).
• Experience with sensor calibration (eye-in-hand/eye-to-hand camera calibration), force-torque sensors, or teleoperation data collection setups.

Qualifications

• Ph.D. in Computer Science, Robotics or a related discipline or Master’s with 3 or more years of industry experience.
• Strong applied expertise in reinforcement learning for robotics, including policy optimization, reward design, training, and evaluation.
• Experience deploying or validating learned policies on physical robots; simulation-only experience is insufficient.
• Experience with sim-to-real transfer and diagnosing discrepancies between simulated and real-world execution.
• Understanding of imitation learning, robot kinematics, control interfaces, and manipulation workflows.
• Comfort working directly with robots and taking ownership of experiments, model training, evaluations, data quality, debugging, and deployment.
• Adaptability and willingness to contribute beyond core model development when required to meet project goals.

Preferred Qualifications

• Experience combining RL with pretrained VLA policies or imitation learning.
• Experience with residual RL, online policy adaptation, failure recovery, or contact-rich manipulation.
• Experience with VLA models such as Pi0/Pi0.5, OpenVLA, Groot, or comparable architectures.
• Experience with industrial or collaborative robots and real-world manufacturing applications is a plus.
• Hands-on experience with Fanuc/UR robots is a plus.

Collaboration & Working Style

• Ownership and Accountability: Take ownership of assigned tasks from problem identification through implementation, testing, and deployment. Proactively identify issues, follow through action items, and communicate blockers early.
• Teamwork: Work effectively with cross-functional teams. Share knowledge, provide constructive feedback, and contribute toward shared project goals.
• Passion for Experimentation: Enjoy testing ideas rapidly, working directly with robots, debugging failures, and turning promising approaches into working solutions. Be willing to iterate repeatedly and learn from unsuccessful experiments.
• Adaptability: Be willing to take on responsibilities beyond core model development, including evaluation, data quality checks, debugging, benchmarking, and experimental setup, based on project priorities.

On-site

• 5x days per week, Mountain View, CA

Compensation

• Salary range: $153,200 to $234,100

Bonus Potential

• An incentive pay program offers payouts based on company performance, job level, and individual performance.

Benefits

• GM offers a variety of health and wellbeing benefit programs. Benefit options include medical, dental, vision, Health Savings Account, Flexible Spending Accounts, retirement savings plan, sickness and accident benefits, life insurance, paid vacation & holidays, tuition assistance programs, employee assistance program, GM vehicle discounts and more.