Robotics ML Engineer (Simulation and Robot Learning)

Noble Machines, Inc•Sunnyvale, CA

1d•$170,000 - $400,000•Onsite

About The Position

Noble Machines builds multipurpose robots to support human workers in the world's toughest jobs—turning dangerous work from a necessity into a choice. Our work demands reliability, robustness, and readiness for the unexpected—on time, every time. We're assembling a mission-driven team focused on delivering real impact in heavy industry, from construction and mining to energy. If you're driven to build rugged, reliable products that solve real-world problems, we'd love to talk. Your defining contribution will be solving the sim-to-real challenge from the simulation side: understanding why policies succeed in simulation but fail on hardware, then improving the environments, data, and training conditions that determine transfer. You will build simulation into a dependable tool for developing industrial autonomy. You will own the learning pipeline end to end, from simulation and data generation through policy training, evaluation, deployment, and iterative improvement on physical robots. The role calls for strong judgment about which aspects of simulation need greater fidelity, which need broader variation, and how to demonstrate that either change improves real-world performance. This is a hands-on ML engineering role with research depth. You will work closely with AI, controls, hardware, and robot operations teammates, owning the learning loop while partnering on the robot, control interfaces, and deployment infrastructure.

Requirements

Demonstrated ability to improve sim-to-real transfer by changing the simulation, data-generation process, or training distribution. You can identify the gap, explain your intervention, and show its effect on physical robot performance.
Hands-on experience training or adapting VLA policies, WAMs, language-conditioned manipulation policies, or other visuomotor policies, with strong practical understanding of imitation learning and reinforcement learning.
Experience building simulation environments or demonstration-generation pipelines for robot learning using tools such as Isaac Sim / Isaac Lab, MuJoCo, robosuite, or comparable systems.
Substantial ownership of a robot-learning pipeline across data, training, evaluation, and hardware deployment (bonus), with evidence of diagnosing failures and improving results.
Strong Python and PyTorch skills, with the engineering discipline to build reproducible training, dataset, and evaluation workflows. Comfortable working with robotics software and reading or modifying C++ when needed.
Practical understanding of robot kinematics, coordinate frames, camera calibration, control interfaces, and the ways embodiment affects learning and transfer.
A PhD, MS, or equivalent hands-on experience in robotics, machine learning, computer science, or a related field. Doctoral research and substantial open-source work count as relevant experience.

Nice To Haves

Experience training or adapting VLA policies or world-action models (WAMs) in simulation and evaluating their transfer to physical robots.
DAgger, intervention-based data collection, offline RL, online RL, or RL fine-tuning of pretrained robot policies.
Bimanual manipulation, mobile manipulation, humanoid task execution, contact-rich tasks, or long-horizon behavior with autonomous recovery.
Distributed training, high-throughput simulation and rendering, or inference optimization on embedded and edge GPUs.

Responsibilities

Lead simulation-side sim-to-real development. Use hardware evidence to identify consequential gaps in visual observations, physics, contact, sensing, and control execution; improve simulation fidelity, calibration, and randomization to address them.
Build and maintain simulation environments and data-generation pipelines for robot learning. Design representative tasks, variations, and evaluation conditions, and ensure generated data is suitable for training transferable policies.
Train and adapt vision-language-action (VLA) policies, world-action models (WAMs), and other visuomotor policies using simulated and real robot data. Build reproducible experiments and make informed choices about data quality, coverage, and training methods.
Close the learning loop between simulation and hardware: analyze failures, collect corrective data, retrain, and validate improvements. Apply DAgger-style data aggregation and human-in-the-loop learning where appropriate.
Use imitation learning and reinforcement learning to improve policy performance, including RL fine-tuning and learning from real-world experience where appropriate.
Design controlled experiments that isolate transfer bottlenecks and distinguish simulator limitations from data, policy, and integration issues. Prioritize simulation improvements by their measured effect on hardware.
Develop repeatable evaluation and regression tests for robustness and generalization. Establish how well simulation results predict hardware performance, and investigate discrepancies.
Deploy, profile, and debug learned policies on robot compute. Improve inference efficiency and reliability, and work with controls and systems teammates to integrate policies with the robot.
Own data and experiment quality across the pipeline, including curation, versioning, reproducibility, and clear reporting of results.