Назад
Company hidden
8 дней назад

Learning-based World Representation (Robotics)

Формат работы
onsite
Тип работы
project
Грейд
trainee
Английский
b2
Страна
Switzerland
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
Learning-based World Representation (Robotics): Investigating how perceptive sensor streams such as RGB images can be encoded into compact latent representations for reconstructing geometry and semantics or supporting downstream robotic tasks with an accent on learned world models and multimodal scene understanding. Focus on designing representations that replace hand-engineered maps, extracting useful information over time, and evaluating embeddings within a mature robotics stack.

Location: Zurich, Switzerland; onsite

Company

hirify.global is a robotics research institute in Zurich collaborating with ETH Zurich on the thesis.

What you will do

  • Investigate learned alternatives to hand-designed grids and scene graphs for representing the world in robotics.
  • Encode streams of perceptive sensor data, such as RGB images, into compact latent representations.
  • Reconstruct features including geometry and semantics from learned representations.
  • Use learned embeddings directly for downstream robotic tasks.
  • Test ideas using a mature robotics stack, multiple robot platforms, and advanced computing infrastructure.

Requirements

  • Master thesis research in robotics and learned world representation.
  • Interest in learning from perceptive sensor data and representing geometry or semantics.
  • Ability to complete the thesis through the collaboration between hirify.global and ETH Zurich.

Culture & Benefits

  • Research environment at the hirify.global with strong engineering support.
  • Access to a mature robotics stack running on multiple robots for fast testing cycles.
  • Best-in-class robotics research laboratory and state-of-the-art computing infrastructure.
  • Onsite thesis work in Zurich.

Hiring process

  • Submit a CV, letter of motivation, and transcripts with the application.
  • Selection is highly competitive; shortlisted candidates are invited to an onsite interview.

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 →