Preference Model is a superintelligence data research company that builds reinforcement-learning environments for training capable, better-aligned AI systems. The company researches ways to improve RL environments and has built environments for several frontier labs. It is backed by $16M in seed funding led by a16z. As a Member of Technical Staff on the ML Platform team, you will own the systems that move an environment from a builder's repository to a partner lab's training run. This includes Karotte, the company's open-source framework for defining RL environments; an internal platform for building, running, and reviewing environments on CPU, GPU, and TPU; and integrations for delivering environments to partner labs. The role focuses on making environment delivery reliable and automated, and ensuring work from the Capabilities team runs and ships cleanly. You will work on a small Platform team alongside environment builders and post-training researchers. The stated first-six-month goal is a mostly automated delivery path to each partner lab, where tasks marked ready are built, validated against lab requirements, and packaged without manual work. The role may also take on other platform and infrastructure priorities as needs change.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
Job Type
Full-time
Career Level
Senior
Education Level
No Education Listed