about 5 hours ago
San Francisco, CA, USA
Staff+
Base Salary
$250k - $350k/yr
Responsibilities
- Design and build RL environments that simulate real-world applications.
- Architect reward functions and verification systems for agent performance.
- Set design patterns and best practices for environment construction.
- Define and enforce quality standards for environments and data.
- Collaborate with researchers to translate post-training goals into requirements.
- Run in-house RL fine-tuning experiments to measure model performance.
- Mentor engineers through code review and architecture guidance.
Requirements
- Hands-on experience with RL fine-tuning and environment design.
- Proficiency in Python and SQL with strong software engineering fundamentals.
- Ability to decompose real-world applications into simulated environments.
- Experience running training experiments and interpreting results.
- Track record of raising engineering quality through mentorship.
- Strong communication skills to engage with ML researchers.
- Advanced degree in Computer Science, Machine Learning, or related field preferred.
Benefits
- Collaborative and supportive work environment.
- Opportunity to work with top talent from leading tech companies.
- Competitive compensation package.
- Flexible working hours.
Tech Stack
PythonSQL
Categories
AI & MLData Science