Research Engineer, Robotics: Physics Simulation and Sim-to-Real (Robotics)
Контакты
128 880 - 193 320$
Формат работы
onsite
Тип работы
fulltime
Грейд
senior
Английский
b2
Страна
US
pythonc++cudareinforcement learningroboticsmujocosim to realrigid body dynamicsphysics simulationcontact solvers
Вакансия из Hirify Global, списка международных tech-компаний Для мэтча и отклика нужен Plus
Пожаловаться
Зарплата и рынок
Нижеразвернуть
$129к-193к/год
$200к$230кмедиана$280к
По похожим ролям (50) ~ $230к/год
На СНГ рынке: $4.2к/мес ($3.1к - $5.2к)
83
Крутая вакансия
развернуть
Узкая исследовательская роль в известном AI-институте дает заметную ответственность, современные инструменты симуляции и заявленную поддержку баланса работы и личной жизни; требования работать в офисе и иметь право на работу в США ограничивают доступность.
Ниже рынка
Четкая специализация
Современный стек
Сильная исследовательская среда
Поддержка баланса
?Только с правом на работу в США
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
Research Engineer, Robotics: Physics Simulation and Sim-to-Real (Robotics): Building stable, accurate physics simulation and sim-to-real validation systems for robot foundation models and manipulation with an accent on contact solvers, rigid-body dynamics, and calibrated simulator behavior. Focus on diagnosing numerical instability, fitting simulation parameters to real-robot data, and scaling GPU-batched simulation across MuJoCo, Newton, and PhysX.
Location: On-site in Seattle, Washington; persons in this role are expected to work from the Seattle offices.
Base salary: $128,880–$193,320 per year, plus bonus plans.
Company
hirify.global is a Seattle-based nonprofit AI research institute developing foundational AI research, open models, data, robotics, conservation, and other technologies for real-world impact.
What you will do
Design, implement, and improve contact, friction, and constraint solvers across MuJoCo, Newton, and PhysX.
Diagnose and eliminate simulation failures including jitter, interpenetration, tunneling, energy gain, constraint drift, stiff-drive instability, and GPU or run-to-run nondeterminism.
Scale and validate physics simulation for GPU-batched training across thousands of environments, including integrator, timestep, substep, stress, and regression testing.
Prepare simulation-ready robot assets with consistent collision geometry, inertial properties, joint limits, contact settings, and descriptions across URDF, MJCF, and OpenUSD.
Fit simulation parameters to logged hardware data and calibrate contact behavior against recorded pushes, slides, grasps, and handovers.
Own sim-to-real correlation testing, trajectory replay, error reporting, domain-randomization ranges, and robot and scene model cards.
Requirements
PhD in robotics, mechanical engineering, applied mathematics, physics, computer graphics, or a related field; alternatively, a master's degree plus 3 years of experience, or a bachelor's degree plus 3 or more years of relevant industry experience.
Demonstrated depth in rigid-body dynamics, constrained multibody systems, articulations, contact and friction modeling, and numerical integration of stiff systems.
Solver or physics-engine code written personally in a research codebase, production engine, or widely used open-source simulator such as MuJoCo, Newton/Warp, PhysX, Drake, Bullet, or Genesis.
Experience diagnosing and fixing simulation instability, including jitter, penetration, energy drift, and divergence, with an understanding of why the fixes work.
Experience fitting simulation parameters to measured data and quantitatively validating results against real-world recordings.
Proficiency in Python and C++, experience with URDF, MJCF, and OpenUSD, and source-level knowledge of at least one major simulation stack.
Must be authorized to work in the United States.
Ability to remain stationary for long periods, communicate and exchange accurate information, observe details at close range, and work under deadlines.
Nice to have
GPU programming for physics using CUDA, NVIDIA Warp, or JAX, and experience scaling simulation for reinforcement or imitation learning.
Experience with deformable, cable, or FEM simulation and coupling with rigid bodies.
Familiarity with differentiable simulation, Bayesian or gradient-based parameter estimation, or learned residual dynamics.
Experience in robot manipulation, grasping, or contact-rich simulation or hardware tasks.
Publications or open-source contributions in simulation, dynamics, or sim-to-real transfer.
Culture & Benefits
Collaborative, transparent, inclusive, and learning-oriented research environment with open models, data, and tools.
Generous paid vacation, sick leave, family leave, and twelve paid holidays.
$125 per month for commuting or internet expenses and $200 per month for fitness and wellbeing expenses.
Annual bonuses and participation in a long-term incentive plan.
Equal opportunity employer offering reasonable accommodations for applicants and employees with disabilities.
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 →