Назад
Company hidden
2 дня назад

Research Scientist, VLA Models - Atlas

177 000 - 225 000$
Формат работы
onsite
Тип работы
fulltime
Грейд
middle
Английский
b2
Страна
US
Вакансия из списка Hirify.GlobalВакансия из Hirify Global, списка международных tech-компаний
Для мэтча и отклика нужен Plus

Мэтч & Сопровод

Для мэтча с этой вакансией нужен Plus

Описание вакансии

Текст:
/
TL;DR
Research Scientist, VLA Models - Atlas (Robotics/AI): Architecting and deploying large-scale vision-language-action and behavior models for dexterous mobile manipulation on the Atlas humanoid with an accent on multimodal robot learning, imitation learning, and real-world deployment. Focus on building scalable training pipelines, enabling few-shot generalization across factory tasks, and integrating learned policies into a physical robot autonomy stack.

Location: Waltham Office, United States of America

Base pay: $177,000–$225,000 annually

Company

hirify.global develops advanced humanoid robots, including Atlas, for general-purpose real-world applications.

What you will do

  • Architect and train end-to-end VLA and Large Behavior Models for mobile manipulation on Atlas.
  • Build imitation learning and behavior cloning pipelines using human demonstrations, teleoperation, and simulation data.
  • Develop pre-training and fine-tuning workflows for multimodal robot learning and precision manipulation tasks.
  • Create policies that generalize across diverse factory manipulation tasks, embodiments, and environments.
  • Integrate learned models into the Atlas autonomy stack with robotics, controls, software, and hardware teams.
  • Deploy, evaluate, and iterate on models using physical hardware; write maintainable Python code for a production codebase.

Requirements

  • MS with 3+ years of experience or PhD in Machine Learning, Robotics, Computer Science, or a related field.
  • Experience training and deploying learned policies for complex behaviors in robots or simulated characters.
  • Strong background in behavior cloning, imitation learning, diffusion policies, World Action Models, and other state-of-the-art methods.
  • Experience with multimodal vision, language, action, and tactile robot learning.
  • Experience with PyTorch, JAX, simulators, and large-scale training workflows.
  • Strong analytical and debugging skills, with the ability to write and review well-structured research code.

Nice to have

  • Hands-on experience deploying learned policies on real robots.
  • Experience creating or curating large robotics datasets, including teleoperation, UMI, and egocentric video.
  • Experience using reinforcement learning as a complementary tool in behavior learning pipelines.
  • Publications in top-tier machine learning or robotics conferences such as CoRL, RSS, ICRA, or NeurIPS.
  • Experience contributing to large C++ or Python codebases.

Culture & Benefits

  • Direct access to an advanced humanoid robot for frequent hardware testing.
  • Collaborative and inclusive team environment that values diverse perspectives and identities.
  • Applied research with real-world impact in general-purpose humanoid robotics.
  • Medical, dental, and vision coverage, 401(k), paid time off, and an annual bonus structure.

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 →