1 день назад
Senior Member of Technical Staff: Reinforcement Learning for Wholebody Control (Robotics)
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
Текст:
TL;DR
Senior Member of Technical Staff: Reinforcement Learning for Wholebody Control (Robotics): Developing and deploying reinforcement-learning policies for humanoid whole-body motion, including balance, locomotion, and coordinated manipulation, with an accent on sim-to-real transfer and integration with classical control. Focus on building scalable training and deployment infrastructure, transferring policies to physical robots, and designing safe evaluation for reliable field behavior.
Location: Cambridge, MA, United States
Company
is building general-purpose humanoid robots for use in homes, workplaces, factories, farms, and other environments.
What you will do
- Design, train, and tune reinforcement-learning policies for humanoid balance, locomotion, and coordinated manipulation.
- Integrate learned policies with classical and model-based control and high-level motion commands.
- Own the sim-to-real pipeline, including domain randomization, system identification, hardware transfer, and real-robot debugging.
- Build infrastructure for repeatable policy training, evaluation, versioning, and deployment.
- Develop rigorous simulation and hardware evaluation, ensuring safe behavior and graceful degradation.
- Collaborate with controls, hardware, simulation, and AI engineers across the robot software stack.
Requirements
- Proven experience developing and training reinforcement-learning policies for continuous control.
- Demonstrated success transferring learned policies from simulation to physical robots and deploying them on real hardware.
- Strong grounding in control theory, robot dynamics, and learned/model-based control integration.
- Hands-on experience with GPU-accelerated simulation at scale.
- Strong Python and working C++ skills for training and deployment infrastructure.
- Experience with whole-body control, locomotion, or manipulation on humanoid, legged, or similarly high-DOF robots.
Nice to have
- Experience with model predictive control, whole-body QP controllers, or trajectory optimization.
- Background in system identification, actuator modeling, or contact-rich dynamics.
- Experience with large-scale ML training infrastructure and experiment tracking.
- Familiarity with imitation learning, teleoperation data, or learning from demonstration.
- Publications or demonstrated results in legged locomotion or whole-body control.
Culture & Benefits
- Competitive total compensation with salary, annual cash bonus, and company equity.
- Company-subsidized insurance programs and a 401(k) with company match.
- Flexible paid time off and daily lunch.
- Collaborative environment grounded in humility and creative technical work.
- participates in E-Verify; employment authorization documents are verified after an offer through the Form I-9 process.
Будьте осторожны: если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого - это мошенники. Обязательно жмите "Пожаловаться" или пишите в поддержку. Подробнее в гайде →
Похожие вакансии
1 день назад
Senior Reinforcement Learning Engineer (Robotics)
2 дня назад
Senior Reinforcement Learning Engineer (Robotics)
2 дня назад
Staff Reinforcement Learning Research Engineer (Robotics)
155 284 - 200 000$
1 день назад
Senior Reinforcement Learning Engineer (Robotics)
230 000 - 260 000$
1 день назад
Reinforcement Learning Engineer (Robotics)
2 дня назад