Job Description
📋 Description Own end-to-end post-training research bets (RL, distillation, long-context) Collaborate with customers with Forward Deployed Engineers to train models Expand collaborations with outside research labs (e.g., ZLab on DFlash) Work with engineering to turn frontier post-training techniques into products Shape the research agenda and guide future directions 🎯 Requirements A research-leaning background in post-training LLMs Enough product sense to tell which frontier techniques matter A record of shipping research that others build on Drive to take a research bet from idea to result with little hand-holding Ability to work in-person in NYC or San Francisco office 🎁 Benefits Equity compensation Collaborative, research-driven culture Production-grade GPU access
