Senior Robotics Research Engineer, Robotics and AI for Drug Discovery

NVIDIA•Santa Clara, CA

About The Position

We are now looking for a Senior Robotics Research Engineer (Robotics & AI for Drug Discovery)! NVIDIA is at the forefront of the AI and robotics revolution, and NVIDIA’s robotics teams are on a mission to build the essential technology that can enable any company to become a robotics company. The Seattle Robotics Lab is focused on fundamental and applied robotics research across the full robotics stack, including perception, planning, control, reinforcement learning, imitation learning, simulation, world models, and multimodal action models. Over the past 9 years, the lab has published 450+ scientific papers that have been presented at top robotics, AI, and computer vision conferences, with a number of these works leading to a transformative impact on robotics research and NVIDIA’s simulation/robotics products. NVIDIA and Eli Lilly have recently announced a groundbreaking partnership to build a co-innovation AI lab to solve the hardest problems in drug discovery. The Seattle Robotics Lab is leading robotics development for this joint effort, focusing on building physical AI for wet labs with scientists in the loop. We are seeking a senior robotics research engineer to develop fundamental robotics technology and build real-world systems that can bring both automation and autonomy to molecular discovery, manufacturing, testing, and validation.

Requirements

A PhD in Robotics, Machine Learning, Computer Science, Electrical Engineering, Mechanical Engineering, or a related field (or equivalent experience).
At least 3 years of research and engineering experience after completing the PhD; 5+ years is preferred.
Deep knowledge of both the theory and practice of robotics and AI, with particularly strong expertise in real-world robotics applications.
Exceptional communication, collaboration, and interpersonal skills, with significant experience working on teams as both a leader and a contributor.
Exceptional programming skills in Python; in addition, familiarity with C++, CUDA, and Warp is a plus.
A track record of writing clean, high-quality code in collaboration with team members, using standard methodologies in software engineering (e.g., unit tests, version control, CI/CD).
Fluency in modern deep learning frameworks such as PyTorch and JAX, as well as training deep learning models on GPU clusters.
Significant experience with robotics frameworks such as ROS2 and physics simulation frameworks such as Isaac Sim, Isaac Lab, and MuJoCo.
Deep comfort in working through the complexities of simulation and real-world robotics, including debugging physics simulators and renderers under rapid development; selecting, setting up, maintaining, and enhancing complex robotics hardware; debugging communication systems (latency, bandwidth, race conditions); and designing robust workflows for model training and evaluation.
A willingness to embrace and experiment with rapidly-developing robotics and AI technology, such as robotics foundation models, world models, and agentic AI as well as rapidly get up-to-speed on biology and chemistry fundamentals, laboratory tasks, laboratory hardware, laboratory automation standards, and safety and regulatory constraints.

Nice To Haves

Direct experience in scientific and laboratory automation is a significant plus.
The following areas of expertise are of particular interest:
Bimanual manipulation
Mobile manipulation and humanoid loco-manipulation
Simulation, sim-to-real, and real-to-sim
Multisensory perception (e.g., vision, force/torque, tactile)
Task and motion planning
Grasp and manipulation planning
Imitation learning and reinforcement learning
High-performance control
Robotics foundation models

Responsibilities

Using NVIDIA Isaac Sim, Isaac Lab, and Matterix to build digital twins of robots, laboratory environments, and scientific procedures
Using NVIDIA Newton to simulate the physics of robots, articulated rigid bodies, deformable objects, granular media, and fluids
Developing perception pipelines for object detection, pose estimation, and tracking, leveraging multisensory inputs (e.g., RGB, depth, force/torque, tactile) and foundation models
Translate experimental protocols into executable physical procedures and smooth, collision-free trajectories by using VLMs and developing task and motion planning pipelines
Training robots to solve contact-rich manipulation tasks through a combination of imitation learning, reinforcement learning, and high-performance control
Building real-world systems that perform discovery, manufacturing, testing, and validation procedures with extremely high reliability and efficiency
Integrating these systems into real-world biological experiment workflows
Collaborating with research scientists in the Seattle Robotics Lab to elevate early-stage research findings and integrate them into a mature automation and autonomy stack
Collaborating with research scientists and engineers in the NVIDIA + Lilly Co-innovation AI Lab with deep expertise across a wide variety of fields (e.g., computational biology and chemistry, generative and agentic AI, bioinformatics, simulation)
Periodically co-authoring publications on technological achievements at high-impact scientific journals and conferences