Назад
Company hidden
10 дней назад

PhD Position on Trustworthy Generalist Robot Policies (AI/Robotics)

Формат работы
onsite
Тип работы
fulltime
Грейд
trainee
Английский
b2
Страна
Italy
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
PhD Position on Trustworthy Generalist Robot Policies (AI/Robotics): Developing trustworthy autonomy methods for generalist robotic systems built on foundation models, with an accent on safety specifications, reliability assessment, runtime assurance, and continual learning. Focus on benchmarking vision-language-action and world-model systems, detecting unsafe behavior, combining learned representations with physical models and constraints, and validating methods in simulation and laboratory robots.

Location: Italy, with research conducted in collaboration with hirify.global and Politecnico di Torino and validation in laboratory settings; the project is associated with the Ellis Unit Turin. Working-hours reference: CET.

Company

hirify.global is a research institute focused on application-oriented artificial intelligence, technology transfer, industrial innovation, and Industry 4.0.

What you will do

  • Characterize failures and diagnose the reliability of generalist robotic systems in novel and safety-critical physical tasks.
  • Review and benchmark foundation-model-based robotic systems, including Vision-Language-Action and world models, to evaluate capabilities and failure modes.
  • Study learned predictions, representations, plans, explanations, and reasoning signals using counterfactual interventions, consistency tests, uncertainty estimation, representation analysis, and targeted post-training.
  • Develop safety specifications and runtime assurance methods using learned safety signals, predictive models, constrained optimization, reachability analysis, and control barrier functions.
  • Design mechanisms that detect, reject, modify, or replace unsafe actions while preserving policy generalization and adaptability.
  • Extend and validate the methods for continual learning in simulation and on real robotic platforms, measuring task success, robustness, risk reduction, latency, and data or supervision requirements.

Requirements

  • Master’s degree, Laurea Magistrale, Laurea Specialistica, or eligible previous-system degree; Italian qualifications require a minimum final grade of 95/110.
  • For foreign qualifications, a degree granting access to PhD studies in the awarding country and meeting the minimum average grade specified in the applicable call.
  • Accepted English language certificate at CEFR B2, unless an exemption in the call applies.
  • Required degree and language certificate may be completed by the deadlines specified in the call.
  • Strong background in machine learning, robotics, computer vision, or control, with solid programming skills in Python.
  • Experience with deep learning frameworks such as PyTorch or JAX.
  • Independence, research motivation, and strong analytical skills.
  • Applicants must also satisfy Politecnico di Torino’s formal PhD admission requirements and submit the official application through the designated portal.

Nice to have

  • Knowledge of foundation models, Vision-Language-Action models, reinforcement learning, imitation learning, or world models.
  • Experience with robotic systems, ROS or ROS 2, MuJoCo or Isaac Sim, optimal control, or model predictive control.

Culture & Benefits

  • Research collaboration with the MIRA Laboratory, Politecnico di Torino, and the Ellis Unit Turin.
  • Access to hirify.global’s Peano high-performance computing infrastructure and state-of-the-art laboratories.
  • Opportunities for research visits at international partner institutions, including Stanford University, MIT, and ETH Zurich.
  • Opportunities to publish at major robotics, machine learning, and artificial intelligence conferences and journals.
  • International research environment, industrial collaborations, startup ecosystem, and competitive salaries with performance-based incentives.

Hiring process

  • Submit a CV covering education, research experience, and technical skills; academic records and Bachelor’s and Master’s diplomas or transcripts; a publication list if applicable; and contact details for at least two referees. Reference letters are not required at this stage.
  • Submit a separate formal application through the official Apply@polito platform; the hirify.global expression of interest does not replace the official application.
  • Deadline: 16 November 2026 at 14:00 CET, for the second session of the 42nd PhD cycle.

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 →