Senior Model Engineer Reinforcement Learning Training Framework
Posted Updated
Description
You will design and implement systems that support reinforcement-learning workloads, profile and debug end-to-end training performance, and improve the scalability and observability of the reinforcement-learning stack.
Responsibilities
- Design and implement systems that support reinforcement learning workloads from small ablations to production training runs
- Profile, debug, and optimize end-to-end training performance
- Improve the scalability and observability of the reinforcement learning stack
Requirements
- Production-quality programming in Python, PyTorch, JAX, Rust, or C++
- Experience training large models, including pre-training, post-training, fine-tuning, or reinforcement learning training of neural networks with more than 1 billion parameters
- Large-scale distributed systems
- Large-scale LLM training infrastructure
- Reinforcement learning numerics
- Reinforcement learning techniques
Benefits
- Equity
- Comprehensive medical coverage
- Vision coverage
- Dental coverage
- 401(k) retirement plan
- Short-term disability insurance
- Long-term disability insurance
- Life insurance
- Discounts and perks
Skills
Sign in to read and join the discussion.