Agent Post-Training Research Engineer (AI)
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
TL;DR
Agent Post-Training Research Engineer (AI): Training frontier models to operate computers, navigate browsers, and use tools with an accent on RL, post-training stacks, and agentic behavior. Focus on building data pipelines, reward signals, and evaluation environments to improve reliability and judgment in long-horizon tasks.
Location: San Francisco, USA
Salary: $295K – $445K
Company
is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity.
What you will do
- Design and run experiments to improve agentic model behavior for complex computer and browser use.
- Own end-to-end improvements to the post-training stack, including RL, data pipelines, graders, and reward signals.
- Build evals and environments to identify model failures and convert them into training data or research directions.
- Collaborate with product teams to translate user signal from Codex and ChatGPT into model improvements.
- Implement early-training and alignment interventions, including data mixtures and synthetic data loops.
- Optimize large-scale training machinery for experiment velocity, reliability, and production readiness.
Requirements
- Strong technical fundamentals in machine learning, software engineering, systems, or statistics.
- Hands-on experience with LLMs, RL, RLHF/RLAIF, post-training, or production ML systems.
- Experience building evals, graders, synthetic data, or coding/tool-using agents.
- Ability to move from vague behavioral problems to concrete hypotheses and experimental pipelines.
- Comfort working across research, product, infrastructure, and safety boundaries.
- Must be based in San Francisco
Culture & Benefits
- High-agency role where work lands directly in frontier models used by millions.
- Environment focused on solving open-ended problems requiring both research taste and engineering execution.
- Culture centered around AI safety, human needs, and diverse perspectives.
- Commitment to equal opportunity and inclusive hiring 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 →