Demonstrated expertise in deep learning with publication record in relevant conferences (e.g., NeurIPS, ICML, ICLR, COLM, ACL, NAACL, EMNLP, ACL) or a track record in applying deep learning techniques to products Proficient programming skills in Python and one of the deep learning toolkits such as JAX, PyTorch, or Tensorflow Ability to work in a collaborative environment. Were solving frontier problems in reward modeling to resist reward hacking, handling sparse and delayed rewards in agentic settings, and aligning models reliably across the spectrum from open-ended creative tasks to precise, action-taking workflows.