13 дней назад
Head of Capability Development (Robotics)
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
Текст:
TL;DR
Head of Capability Development (Robotics) (bipedal locomanipulation): Leading the development of reliable robot capabilities for household and service tasks with an accent on applied deep learning, real-robot deployment, and team leadership. Focus on training policies, coordinating whole-body control and VLA model development, driving sim-to-real transfer, and diagnosing failures across policy, controller, and data.
Location: San Diego, California, United States; on-site
Company
develops commercially scalable and safe robots, including the HMND-01 platform for real industrial environments.
What you will do
- Own the capability roadmap for bipedal locomanipulation tasks in homes and service environments, defining priorities, execution strategies, evaluations, and delivery timelines.
- Hire, develop, and manage a team of robot learning engineers while setting engineering and experimentation standards.
- Coordinate with Controls on policy commands, whole-body control, teleoperation, and failure diagnosis across the policy-controller boundary.
- Define data requirements, supervise bipedal data collection, and ensure sufficient diversity and task coverage.
- Drive reinforcement learning and sim-to-real transfer using the digital twin, reward design, and simulation improvements.
- Feed bipedal requirements into VLA foundation model development and inform future hardware designs for hands, arms, and legs.
Requirements
- 5+ years working on robots, including learned manipulation or locomanipulation policies deployed on real hardware.
- Experience leading a team of 5+ applied robot learning engineers, including hiring, people management, and deadline-driven delivery.
- Recent hands-on experience training and debugging policies, curating data, post-training policies, and diagnosing robot failures.
- Experience post-training VLA-class policies with behavior cloning or reinforcement learning, plus experience with deep learning infrastructure, PyTorch, or JAX.
- Strong understanding of whole-body control, inverse kinematics, RL locomotion controllers, teleoperation, and modern robotics software engineering.
Nice to have
- Experience with multi-fingered dexterous hands, tactile sensing, retargeting, and in-hand manipulation.
- Experience with bipedal locomotion, teleoperation, and reinforcement learning on simulated or real robots.
- Familiarity with Physical Intelligence π models, NVIDIA GR00T, or similar open VLA frameworks.
- Top-tier robotics or deep learning publications, or equivalent open-source contributions.
Culture & Benefits
- US-based employees receive fully paid medical, dental, and vision insurance, with virtual care and employee assistance resources.
- 23 days of accrued PTO, separate sick leave, and paid company holidays.
- 401(k) plan with a 4% employer match and stock options.
- Free daily catered lunch, snacks, and drinks in the office.
- Work with engineers, researchers, and product experts in AI and robotics, with ownership of key initiatives.
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 →