Назад
Company hidden
3 дня назад

Data & Model Quality Engineer (Robotics)

Формат работы
hybrid
Тип работы
fulltime
Грейд
senior
Английский
b2
Страна
Japan
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
Data & Model Quality Engineer (Robotics): Training and evaluating robotics models while defining data-quality standards, building quality tools, and improving multimodal datasets for reliable real-world robot operation with an accent on hyperparameter tuning, checkpoint selection, evaluation statistics, and data collection strategy. Focus on designing automated evaluation and data-quality infrastructure, identifying failure modes, and translating technical findings into practical collection guidelines for operators.

Location: Tokyo, Japan; hybrid

Company

hirify.global develops humanoid robotics products and systems for reliable real-world robot operation.

What you will do

  • Train robotics models across hyperparameter configurations and select stable, reliable checkpoints using reproducible experiments.
  • Evaluate models and datasets through success rates, failure modes, variance analysis, metrics, and KPIs.
  • Define good and bad data, identify problematic multimodal samples, and improve dataset quality.
  • Use evaluation results to set future data-collection priorities and provide regular feedback to Operations.
  • Build tools, methods, pipelines, and infrastructure for automated data-quality and model evaluation.
  • Collaborate with Hardware, Operations, and System Engineering teams while introducing useful advances in robot learning, data curation, and evaluation.

Requirements

  • Experience training models for robotics control, including hyperparameter tuning.
  • Ability to understand model architectures and approaches and use that understanding to tune hyperparameters and improve performance.
  • Experience reviewing data, identifying problematic parts, and improving data quality, ideally with multimodal data including images, video, trajectories, and sensor logs.
  • Experience working in a fast-paced, high-output environment.
  • Strong Python programming skills.
  • Strong English communication skills.

Nice to have

  • Experience with vision-language, vision-language-action, or other large multimodal models.
  • Familiarity with robotics software stacks, ROS1/2, or Jetson-class platforms.
  • Experience with distributed training or production ML infrastructure.
  • Systems thinking covering model behavior, control, safety, and system boundaries.
  • Japanese language skills.

Culture & Benefits

  • Full-time employee position in a hybrid workplace.
  • Ownership of outcomes and a user-centric mindset.
  • High-performance, high-accountability environment.
  • Ability to turn technical findings into clear instructions for operators and other non-engineers.

Hiring process

  • Optional supplementary evidence may include a project portfolio or demos, data-quality tools and results, model training and evaluation work, and operational outcomes beyond proof-of-concept or research-only settings.

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 →