Open role
Member of Technical Staff - Research Engineer, Post-training
Preference Model
About this role
Preference Model is seeking a Research Engineer to push the boundaries of self-directed learning in large language models. You will implement novel approaches, shape research directions, and train/evaluate models on proprietary RL environments. This role blends research and engineering, requiring you to optimize training infrastructure and design new methodologies.
What we are looking for 6
- Train and evaluate LLMs on proprietary RL environments
- Architect and optimize RL training infrastructure
- Design, implement, and test RL training environments and methodologies
- Profile and optimize training runs for maximum throughput
- Industry experience running end-to-end LLM post-training pipelines (7B+ models)
- Proficiency in Python and PyTorch or JAX