About the job
Intrinsic Robotics is a pioneering initiative under Alphabet, dedicated to transforming the landscape of industrial robotics. We are driven by the belief that breakthroughs in AI, perception, and simulation will revolutionize industrial robotics, placing software and data at the forefront of this evolution.
Our mission is to empower businesses, entrepreneurs, and developers by making industrial robotics smarter, more accessible, and user-friendly. We comprise a dynamic team of engineers, roboticists, designers, and technologists, all passionate about unleashing the creative and economic potential of industrial robotics.
Role
As a Robotics Software Engineer with a focus on Robot Learning and Manipulation, you will spearhead the design, training, validation, and deployment of contact-rich manipulation skills tailored for real-world manufacturing applications. You will concentrate on tackling dexterous, contact-rich assembly challenges. Your responsibilities will include developing and integrating advanced sensor-based control strategies and Machine Learning (ML) policies within the Intrinsic Robot Control stack. This encompasses managing the entire model lifecycle—from architecture and large-scale data collection to training, validation, deployment, and optimization to meet stringent industrial standards.
How your work moves the mission forward
- Develop, train, and deploy multi-modal feedback and interaction controllers aimed at solving high-precision insertion and assembly tasks.
- Lead the AI manipulation model lifecycle, conducting regular trials on industrial hardware to assess algorithmic modifications and curate high-quality training datasets.
- Design and build modular components for reinforcement and imitation learning, continually striving to enhance the robustness of contact-rich assembly tasks.
- Stress-test and optimize the real-time execution framework for learned manipulation models within the Intrinsic platform.
Skills you will need to be successful
- A PhD or equivalent professional experience in Robot Learning and AI Manipulation (such as Applied Reinforcement Learning, Visuomotor Policy Learning, or Vision-Language-Action models).
- At least 2 years of professional experience in C++ and Python, with a proven history of delivering production-quality code.
- Deep expertise in ML Frameworks: JAX, TensorFlow, or PyTorch.
- Hands-on experience with hardware, specifically testing and iterating on physical robots equipped with vision and force-torque sensors.
- Operational grit: A strong desire to spend significant time in the lab, managing hardware experiments and troubleshooting issues.