Member of Technical Staff - Research Engineer, Post-training

Preference Model is seeking a Research Engineer to push the boundaries of post-training for large language models. In this role, you will implement novel approaches, shape research directions, and train/evaluate models on proprietary RL environments. This position blends research and engineering, focusing on self-directed learning and improving AI alignment.

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