Member of Technical Staff — Simulation & Robot Learning Engineer

Location: New York, NY — Onsite
Employment Type: Full-time
Team: Robot Learning / Software

About the Role

We are building and deploying humanoid robots designed to operate on real factory floors and perform meaningful work in demanding production environments. Simulation is a critical part of making these systems deployment-ready quickly, allowing us to develop, train, evaluate, and iterate on robotic behaviors at scale.

We are looking for a Member of Technical Staff (Simulation & Robot Learning Engineer) to build high-fidelity simulation environments, develop scalable data-generation pipelines, train robot-learning policies, and close the sim-to-real gap so that behaviors developed in simulation translate reliably to physical robots.

As a Member of Technical Staff (Simulation & Robot Learning Engineer), you will own the pipeline from simulation environments and task authoring through data generation, policy training, evaluation, and deployment. You will work across reinforcement learning, imitation and diffusion policies, Vision-Language-Action models, world models, and emerging agentic AI techniques.

This is a hands-on individual contributor position for a Member of Technical Staff (Simulation & Robot Learning Engineer) who enjoys working across simulation, machine learning, robotics, and physical hardware. You should be comfortable building environments from scratch, tuning physics and contact models, scaling training infrastructure, and debugging the difficult gap between simulation and reality.

You will work on challenging manipulation problems involving rigid, articulated, and deformable objects, across single-arm, bimanual, whole-body, and wheeled humanoid platforms.

What You'll Do

Build and maintain high-fidelity simulation environments using platforms such as Isaac Sim/Lab, MuJoCo, Drake, Gazebo, SAPIEN, Genesis, or similar tools.
Author scenes, assets, physics configurations, contact models, and task definitions for robotic manipulation.
Train deployable robot policies using reinforcement learning, imitation learning, diffusion policies, VLAs, world models, and related approaches.
Drive policies from simulation onto physical robots and improve their robustness in real-world operation.
Close the sim-to-real gap using domain randomization, system identification, real-to-sim calibration, physics tuning, and systematic hardware debugging.
Build scalable pipelines for synthetic data generation, teleoperation and demonstration collection, procedural scene and task generation, and automated training curricula.
Use agentic AI and LLM-based tooling to automate simulation and data workflows, including environment generation, task creation, reward design, randomization configuration, evaluation, and curriculum generation.
Develop systems that allow simulation and learning experiments to iterate in hours rather than weeks.
Work on challenging manipulation regimes involving rigid, articulated, and deformable objects such as cloth, cables, and soft materials.
Build evaluation and benchmarking infrastructure that makes simulation performance a trustworthy indicator of real-world robot performance.
Work closely with controls, perception, mechanical, and other learning engineers to translate target behaviors into smooth, safe, and repeatable robot motion.
Help establish scalable infrastructure and engineering practices for robot learning and simulation.

Required Qualifications

BS, MS, or PhD in Robotics, Computer Science, Machine Learning, Electrical Engineering, Mechanical Engineering, Aerospace Engineering, or a related technical field.
4+ years of hands-on experience building simulation environments and training or deploying robot-learning policies on physical hardware. Equivalent advanced research or project experience may be considered.
Deep experience with at least one major robotics simulator, such as Isaac Sim/Lab, MuJoCo, Drake, Gazebo, SAPIEN, Genesis, or a comparable platform.
Experience building and tuning simulation environments rather than simply using pre-existing environments.
Demonstrated experience with sim-to-real transfer, including domain randomization, system identification, calibration, and diagnosing simulation-to-hardware discrepancies.
Strong understanding of modern robot learning, including reinforcement learning and/or imitation or diffusion-based policies.
Working familiarity with Vision-Language-Action models and/or world models.
Experience scaling data generation and collection for robot-learning systems, including synthetic data, procedural generation, teleoperation, or demonstration pipelines.
Strong Python skills and comfort working with C++ when required.
Proficiency with PyTorch, JAX, or comparable machine-learning frameworks and tooling.
Demonstrated ability to get robot-learning systems working reliably on physical hardware.
Experience with manipulation involving robotic arms, bimanual systems, humanoids, or comparable platforms.

Nice to Have

Experience using agentic or LLM-based systems to automate simulation and data workflows.
Experience with automated reward generation, Eureka-style approaches, automated scene and task generation, agentic evaluation, or curriculum design.
Deformable-object manipulation experience, including cloth, cables, soft bodies, and other contact-rich environments.
Experience with Vision-Language-Action systems such as OpenVLA, ?0, RT-style policies, or comparable architectures.
Experience with world models for robotics and manipulation.
Bimanual, whole-body, or wheeled-humanoid manipulation experience.
GPU-accelerated or massively parallel simulation experience.
Experience with large-scale reinforcement-learning training.
Real-time or on-robot deployment experience.
Familiarity with robotic controls and hardware stacks, including the interfaces between learned policies and low-level controllers.
Publications, open-source contributions, competition results, or other demonstrated work in robot learning or simulation.

What We're Looking For

The ideal Member of Technical Staff (Simulation & Robot Learning Engineer) combines strong robotics and machine-learning fundamentals with practical engineering judgment. You should enjoy building systems from the ground up, scaling experiments, and investigating why a behavior that works perfectly in simulation fails on a physical robot.

We are looking for someone who takes ownership of the full simulation-to-deployment loop and is excited by the opportunity to combine high-fidelity simulation, large-scale data generation, modern robot learning, and real-world robotics.

We welcome applicants from all backgrounds and are committed to building an inclusive and equal-opportunity workplace.