обновлено 15 дней назад
Reinforcement Learning Intern (AI)
Вакансия из Hirify Global, списка международных tech-компанийДля мэтча и отклика нужен Plus
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
Текст:
TL;DR
Reinforcement Learning Intern (AI) (Python/Gym/Unreal Engine): Developing autonomous agents that interact with and learn from virtual environments for gameplay and automated testing, with an accent on environment integration, reward design, policy training, and evaluation. Focus on implementing reinforcement learning pipelines, optimizing policies, measuring learning efficiency, and interpreting experimental results.
Location: Singapore Razer AI Center
Company
Razer develops gaming products and technologies through global, gamer-centric teams.
What you will do
- Design, train, and evaluate reinforcement learning agents using Gym or Unreal Engine.
- Integrate virtual environments and develop agents for gameplay and automated testing.
- Implement and test reward functions, policy optimization methods, and training pipelines.
- Run experiments to measure agent performance and learning efficiency.
- Collaborate with mentors to refine models, interpret experimental data, and document findings.
Requirements
- Currently pursuing a Bachelor's or Master's degree in Computer Science, AI, or a related field.
- Proficiency in Python and familiarity with machine learning fundamentals.
- Strong analytical thinking, curiosity, and self-motivation.
- Availability for a minimum 16–20 week internship.
Nice to have
- Coursework or experience in reinforcement learning or simulation-based AI.
- Knowledge of Q-learning, PPO, DQN, or related reinforcement learning algorithms.
Culture & Benefits
- Full-time position within a global AI Software team.
- Opportunity to work with teams across five continents.
- Inclusive and respectful workplace with equal employment opportunity.
- Reasonable accommodations are provided where needed for disability or religious practices.
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 →