Description
We are seeking a Research Scientist to join our team, focusing on reinforcement learning research and development.
The successful candidate will design and run rigorous experiments to improve model capability, develop data recipes, and define evaluation metrics.
Responsibilities:
- Design and run experiments to measure gains in model capability
- Improve data quality and recipes through deduplication and mixture experiments
- Develop evaluation metrics and grader design
- Advance training science, including architecture and scaling experiments
- Build evaluations and targeted tasks to expose model weaknesses
- Collaborate with engineers to scale experiments
Basic Qualifications:
- Experience writing production-quality code in Python, PyTorch, JAX, Rust, or C++
Preferred Skills and Experience:
- Experience with reinforcement learning algorithms and language models
- Strong background in machine learning fundamentals
- Excellent programming skills in Python and PyTorch or JAX
- Experience with distributed training at scale
- Track record of original work in machine learning
- MS or PhD in Computer Science, Machine Learning, or a related field
Additional Requirements:
- Must be able to work onsite in Palo Alto
Compensation and Benefits:
- Annual salary: $160,000 - $250,000 USD
- Comprehensive benefits package, including equity, medical, vision, and dental coverage, 401(k) retirement plan, and other perks
For more fresh new jobs, check out yubhub.co.