Senior Physical AI & Robotics Scientist - Lab Automation
Roche
Summary
At Genentech (gRED) and Roche (pRED), we're applying Physical AI to solve one of humanity's hardest challenges: building fully autonomous, self-healing laboratories for lights-out drug discovery. The Computational Sciences Center of Excellence (CoE) and the Data and Digital Catalyst (DDC) team are building the foundational platform for autonomous labs – turning state-of-the-art AI into real-world physical action to deliver life-saving medicines to patients faster than ever before.
Job description
As a Senior Physical AI & Robotics Scientist, you will be the hands-on technical lead and scientific architect bringing Physical AI to life – deploying 3D perception, multi-physics digital twins, edge vision, and closed-loop control onto state-of-the-art robotic hardware using cutting-edge stacks like NVIDIA Isaac, Omniverse, and Metropolis.
In this role, you will:
- Develop 3D computer vision perception pipelines (point clouds, depth maps, pose estimation) and dynamic motion planning algorithms (ROS 2, MoveIt 2, cuMotion) to enable reliable arm manipulation, hand-eye calibration, grasping, and AMR navigation in dynamic workcells.
- Build multi-physics simulation environments (NVIDIA Isaac Sim/Lab, Newton Engine) to model robot-labware interactions, evaluate LLM-generated execution plans inside digital twins before deployment, and train policy recovery models.
- Apply system identification, domain randomization, and sim-to-real tuning to ensure simulation-trained control policies execute predictably on physical hardware.
- Fine-tune multimodal Vision AI models (VLMs, NVIDIA Cosmos) using synthetic failure datasets (Isaac Sim) for real-time detection of lab anomaly modes (spills, bubbles, dropped microplates, tilted lids, tip-pick misses).
- Optimize low-latency inference with TensorRT on NVIDIA Jetson (Thor/Orin) edge hardware, combining visual servoing and closed-loop feedback control so systems self-correct without halting master workflows.
- Harness OpenUSD scene graphs to represent workcell geometry and state, integrating synchronization services to link executable digital twins across heterogeneous hardware APIs (SiLA 2, gRPC, vendor SDKs).
Who You Are
Core Qualifications & Experience
- MS in Computer Science, Robotics, Electrical Engineering, Mechanical Engineering, or related technical field with 5+ years of experience, or a PhD with 2+ years of experience in deploying Physical AI or robotics solutions.
- Strong interest in translating physical AI capabilities into biological workflows and drug discovery pipelines.
- Passionate builder with a proven track record of taking real-world robotic manipulation and sim-to-real systems beyond demonstrations into sustained operation.
- Strong background in 3D computer vision, kinematics, motion planning (ROS 2, MoveIt 2, cuMotion), and modern machine learning frameworks (PyTorch) with strong C++/Python skills.
- Hands-on experience with robotics simulation and robot-learning frameworks (NVIDIA Isaac Sim/Lab, Newton, MuJoCo, Drake, Gazebo) and sim-to-real validation methods.
- Experience training or fine-tuning vision/multimodal models (VLMs, Cosmos) and optimizing neural networks with TensorRT for edge hardware (Jetson Thor/Orin).
- Proficiency with visual servoing, closed-loop controllers, and hardware API integration (gRPC, SiLA 2, vendor SDKs).
Preferred but not required
- Hands-on experience with OpenUSD scene graphs, custom USD schemas, or NVIDIA Omniverse workflows.
- Experience working with high-throughput lab automation hardware, manipulators, or liquid handlers (e.g., Hamilton, Tecan, Precise Automation, UR arms).
- Background in imitation learning, reinforcement learning, or robot foundation models for contact-rich manipulation and recovery.
- A public portfolio of real-world projects on GitHub/GitLab showcasing work in robotics, simulation, or physical AI.
Requirements
- MS in Computer Science, Robotics, Electrical Engineering, Mechanical Engineering, or related technical field with 5+ years of experience, or a PhD with 2+ years of experience in deploying Physical AI or robotics solutions.
- Strong interest in translating physical AI capabilities into biological workflows and drug discovery pipelines.
- Passionate builder with a proven track record of taking real-world robotic manipulation and sim-to-real systems beyond demonstrations into sustained operation.
- Strong background in 3D computer vision, kinematics, motion planning (ROS 2, MoveIt 2, cuMotion), and modern machine learning frameworks (PyTorch) with strong C++/Python skills.
- Hands-on experience with robotics simulation and robot-learning frameworks (NVIDIA Isaac Sim/Lab, Newton, MuJoCo, Drake, Gazebo) and sim-to-real validation methods.
- Experience training or fine-tuning vision/multimodal models (VLMs, Cosmos) and optimizing neural networks with TensorRT for edge hardware (Jetson Thor/Orin).
- Proficiency with visual servoing, closed-loop controllers, and hardware API integration (gRPC, SiLA 2, vendor SDKs).
- Hands-on experience with OpenUSD scene graphs, custom USD schemas, or NVIDIA Omniverse workflows.
- Experience working with high-throughput lab automation hardware, manipulators, or liquid handlers (e.g., Hamilton, Tecan, Precise Automation, UR arms).
- Background in imitation learning, reinforcement learning, or robot foundation models for contact-rich manipulation and recovery.
- A public portfolio of real-world projects on GitHub/GitLab showcasing work in robotics, simulation, or physical AI.
Benefits
- Annual bonus
- Relocation benefits not available
Company overview
Roche is a Swiss multinational healthcare company and a global pioneer in pharmaceuticals and diagnostics, founded in 1896 and headquartered in Basel, Switzerland. As the world's largest biotech company and the fifth-largest pharmaceutical company by revenue, Roche operates through two primary divisions: Pharmaceuticals and Diagnostics. The company is renowned for its leadership in personalized healthcare, combining strengths in both drug development and diagnostic testing to deliver tailored treatments for patients. Roche maintains a strong focus on oncology, immunology, infectious diseases, ophthalmology, and central nervous system disorders, with a portfolio that includes over 30 medicines on the World Health Organization's Model Lists of Essential Medicines. The company owns significant subsidiaries including Genentech, Chugai Pharmaceuticals, Ventana Medical Systems, and Foundation Medicine. With approximately 103,000 employees worldwide and operations in over 100 countries, Roche has established itself as a leader in cancer treatments globally while maintaining a robust pipeline of innovative therapies and diagnostic solutions. The company's commitment to sustainability has been recognized through ten consecutive years as Group Leader in the Dow Jones Sustainability Indices within the Pharmaceuticals, Biotechnology & Life Sciences Industry.