Similar Jobs

See all

Role Focus:

  • Own experiments from data and design through training, evaluation, and reporting.
  • Spend roughly half the role on reinforcement learning and model training.

Responsibilities:

  • Design RL environments, reward functions, and verifiers; fine-tune language models.
  • Build evaluation frameworks, run experiments, and document results.

Qualifications:

  • Strong Python, PyTorch, Hugging Face, and fine-tuning experience.
  • Demonstrated RL, LLM evaluation, and domain-expert collaboration.
Apply for This Position