Member of Technical Staff - Research & Post-training

Preference Model is seeking a Research Engineer to advance self-directed learning in large language models. You will implement novel approaches, shape research directions, and train/evaluate models using proprietary RL environments. This role involves architecting and optimizing RL training infrastructure and improving research iteration cycles.

• Train and evaluate models 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 throughput
• Experience running LLM post-training pipelines (7B+ models)
• Proficiency in Python and PyTorch or JAX