Staff/Senior Reinforcement Learning Engineer (Industrial Assembly)

Role

As a Staff/Senior Reinforcement Learning Engineer at Intrinsic, you will lead the end-to-end lifecycle of developing and deploying RL for complex industrial assembly tasks. You will research and implement sample-efficient algorithms with a strong focus on production-grade reliability and robustness. Working within the Engineering organization, you will drive rapid tech transfer from research into production, taking full ownership of the performance and operational success of learned controllers in our customers’ factories worldwide. Leveraging Intrinsic’s world-class infrastructure and robotics capabilities, you will contribute to elevating AI manipulation from the experimentation stage to unlock novel industrial automation paradigms.

How your work moves the mission forward

• Develop, mature, and deploy production-grade RL policies that solve contact-rich assembly tasks on real-world manufacturing lines using industrial robots.
• Transition cutting-edge manipulation research into robust, scalable production solutions with high velocity.
• Define the roadmap and take ownership of the future development of our Reinforcement Learning Algorithms stack for global industrial deployment.
• Contribute to our cloud and on-premises training workflows required for large-scale model/policy optimization.

Skills you will need to be successful

• Domain and Industry Experience: PhD in applied Reinforcement Learning, Visuomotor Policy Learning, or a related field with a focus on robotic manipulation and industrial assembly, complemented by 3+ years of relevant industry experience.
• Deep Learning & Software: Advanced proficiency in JAX, Python, and C++. Extensive experience with TensorFlow or PyTorch.
• Scientific Excellence: A strong theoretical foundation in state-of-the-art algorithms, evidenced by high-impact publications in the robot learning community (e.g., CoRL, RSS, ICRA).
• Deployment Know-How: A proven track record of successfully transferring RL algorithms from the experimental stage to production-grade industrial applications.

Skills that will differentiate your candidacy

• Advanced Policy Learning: Experience with Diffusion Policies, World Models, Vision-Language-Action (VLA) models, or Offline RL.
• Multimodal Perception and Control: Expertise in integrating tactile/force sensing (force control) and computer vision (visual servoing) for contact-rich tasks.
• Complex Manipulation: Experience handling soft or linear deformable objects and/or utilizing data augmentation for robust policy training.
• Large-Scale Training: Proficiency in training on massive multimodal datasets and managing cloud-based training workflows (e.g., Argo).
• Industrial Robotics Expertise: Hands-on experience with industrial-grade automation equipment and familiarity with safety standards in production environments.
• Customer Focus: Willingness to travel internationally to analyze customer use cases and deploy solutions under ambitious timelines.