Preference Model

Preference Model seeks a Research Engineer in San Francisco to design RL environments and reward functions for frontier LLMs. Requires 5+ years ML experience, Python, PyTorch/JAX. Top-tier pay, equity, and autonomy.

Build scalable ML infrastructure for RL post-training at a superintelligence data research company in San Francisco. Requires deep LLM inference/training expertise (vLLM, PyTorch, distributed systems) plus strong software engineering fundamentals.