Research Scientist 4 - Machine Learning and Inference Research (LLM Post-Training)

Lead research on post-training LLMs for downstream tasks, focusing on RL-based methods (RLHF, RLVR) and related improvements (reasoning, alignment, distillation).
Design, run, and evaluate experiments to enhance performance, memory, calibration, and tool usage in deployed models.
Collaborate across cross-functional teams to translate research into scalable, real-world impact and inform product decisions.
Publish at top venues, present at conferences, and mentor interns while sustaining an open culture of innovation.
Develop and articulate a coherent research agenda, communicate findings to diverse audiences, and guide adoption of new methods.
Contribute to elevating the broader organization by sharing knowledge and fostering lasting collaborations.