Senior Physical AI & Robotics Scientist - Lab Automation
genentechMillbrae (CA)
Senior Physical AI & Robotics Scientist - Lab Automation
Posted today
genentechMillbrae (CA)
SENIORITY
Senior
About the role
Overview:
In this role you drive Physical AI for autonomous, lights-out lab operations, leading technical architecture and deployment on robotic hardware. You will bridge foundation AI with real-world devices to enable scalable, autonomous laboratories at global scale. Partnering with gRED and pRED teams, you shape perception, planning, and control pipelines to accelerate drug discovery. You work hands-on to turn simulation-based policies into reliable lab automation. This is a high-impact opportunity to push the frontier of AI-enabled biology at Roche. Compensation / Benefits discretionary annual bonus comprehensive company benefits (per link)
Responsibilities:
Develop 3D vision perception and dynamic motion planning for robotic manipulation and navigation in dynamic workcells Create multi-physics simulation environments to model robot-labware interactions and evaluate AI plans in digital twins Apply sim-to-real tuning and system identification to ensure real hardware follows simulation-trained policies Fine-tune multimodal vision models using synthetic failure data for real-time anomaly detection in the lab Optimize low-latency edge inference and closed-loop control on NVIDIA Jetson hardware Use OpenUSD scene graphs and synchronization services to integrate workcell geometry across diverse hardware APIs
Key requirements:
MS in Computer Science, Robotics, Electrical Engineering, Mechanical Engineering, or related field with 5+ years of experience, or PhD with 2+ years Strong background in 3D computer vision, kinematics, motion planning (ROS 2, MoveIt 2, cuMotion) Proficiency in PyTorch and C++/Python with robotics simulation frameworks (NVIDIA Isaac Sim/Lab, Newton, MuJoCo, Drake, Gazebo) Experience training or fine-tuning vision/multimodal models (VLMs, Cosmos) and optimizing networks with TensorRT for edge hardware Proficiency in visual servoing, closed-loop controllers, and hardware API integration (gRPC, SiLA 2, vendor SDKs) 3D computer vision ROS 2 MoveIt 2 cuMotion PyTorch NVIDIA Isaac Sim/Lab
Before you apply
Applying takes about a minute. These four things decide how fast it moves after that.
Your profile is current
It's what we read first. Occupations, seniority and locations matter more than a long history.
Two examples you can talk through
Not a portfolio — just two pieces of work where you can explain the decisions and what you'd change.
A number in mind
What you're on now and what would make you move. We negotiate better when we know both.
Your notice period
Employers plan around it, and it's the question that stalls offers most often.
Once you apply, someone reads it and calls you before anything reaches the employer — usually within two working days.