Who you are:
- A physics-minded engineer who treats simulation fidelity as an engineering discipline, not an afterthought
- Rigorous about system identification - you fit models to measured data
- A natural bridge between the hardware lab and the training cluster
Responsibilities:
- Build and maintain the robot's digital twin (URDF/MJCF/USD) directly from the team's CAD, tracking every hardware revision
- Model actuators from real dyno data: torque-speed envelopes, friction, backlash, latency, and thermal limits - so trained policies never demand what hardware cannot deliver
- Run system identification campaigns against the physical robot together with motion control and V&V
- Design domain randomization strategies and simulation environments in Isaac Sim with the Newton physics engine, together with the RL engineer
- Own the sim-to-hardware deployment pipeline together with the compute platform engineer: export, validation, and on-robot evaluation protocols
- Quantify and continuously reduce the sim-to-real gap with defined metrics
- Generate synthetic data and scenario suites for training and regression testing
Requirements:
- M.Sc. (or equivalent experience) in Robotics, Mechanical/Electrical Engineering, or Computer Science
- 4+ years with physics simulation for robotics: Isaac Sim/Newton, MuJoCo, or equivalent
- Strong Python; solid grasp of rigid-body dynamics, contact modeling, and actuator dynamics
- Hands-on system identification experience against physical hardware
- Experience supporting RL policy transfer to real robots (domain randomization, dynamics randomization, actuator modeling)
Advantages:
- Sim2Real work on legged or humanoid robots
- Experience with USD pipelines and CAD-to-sim automation
- Familiarity with Motor Operating Region style actuator-constraint modeling in training
- C++ for high-performance simulation components
- Comfortable communicating technical topics in English with international teams
Skills Required
- M.Sc. (or equivalent experience) in Robotics, Mechanical/Electrical Engineering, or Computer Science
- 4+ years with physics simulation for robotics: Isaac Sim/Newton, MuJoCo, or equivalent
- Strong Python
- Solid grasp of rigid-body dynamics, contact modeling, and actuator dynamics
- Hands-on system identification experience against physical hardware
- Experience supporting RL policy transfer to real robots (domain randomization, dynamics randomization, actuator modeling)
What We Do
Mobileye is leading the mobility revolution with its autonomous-driving and driver-assistance technologies, harnessing world-renowned expertise in computer vision, machine learning, mapping, and data analysis. Founded in 1999, Mobileye has pioneered such groundbreaking technologies as REM™ crowdsourced mapping, True Redundancy™ sensing, and the RSS™ safety model. These technologies are driving the ADAS and AV fields towards the future of mobility – enabling self-driving vehicles and mobility solutions, powering industry-leading advanced driver-assistance systems and delivering valuable intelligence to optimize mobility infrastructure. Mobileye technology is used in over 170 million vehicles worldwide. In 2022, Mobileye became an independent company while still being majority-owned by Intel. Mobileye’s headquarters and R&D center are based in Jerusalem, with additional offices across Israel and around the world.
Why Work With Us
Our technology enables self-driving vehicles and mobility solutions, powers industry-leading advanced driver assistance systems, and delivers valuable intelligence to optimize mobility infrastructure.
Gallery
