12 дней назад
Software Engineer (AI/RL Environments)
150 000 - 190 000$
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
Software Engineer (AI/RL Environments): Building reinforcement learning environments, simulations, reward signals, evaluation systems, and data pipelines for training advanced AI models with an accent on RLHF/RLVR, production engineering, and model evaluation. Focus on analyzing agent failure modes, running post-training experiments, and translating research objectives into deployable systems.
Location: San Francisco, United States — onsite
Salary: $150,000–$190,000 per year
Company
Applied AI research company working with frontier model labs to improve advanced models.
What you will do
- Build reinforcement learning environments, simulations, and task frameworks.
- Develop reward signals and evaluation systems for RLHF and RLVR.
- Analyze model and agent failure modes and run post-training experiments.
- Build synthetic and real-world data pipelines.
- Work with researchers to translate training objectives into production systems.
Requirements
- Strong experience with reinforcement learning.
- Experience building environments, reward systems, or model evaluations.
- Strong Python engineering skills.
- Ability to build and deploy production systems.
- Experience with Docker, Kubernetes, or similar infrastructure.
- Primarily 1–5 years of experience; exceptional new graduates may be considered.
Nice to have
- Experience in RL environments, AI evaluation, benchmarking, or AI safety.
- High-growth startup, early engineering, or founder experience.
- Exceptional technical achievements or standout internships.
Culture & Benefits
- Fast-moving environment with high ownership.
- Direct collaboration with researchers and frontier model labs.
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 →