Preference Model builds RL environments that automate ML research and engineering.
Sur place · Toronto
Design and scale compute, scheduling, and data infrastructure to power post-training research on in-house RL environments. Develop core ML framework primitives and evaluation tooling to accelerate reproducible experimentation for research engineers.
Sur place · Toronto
Design and build low-level reinforcement learning environments targeting GPU and accelerator kernels. Develop deterministic scoring and sandboxing infrastructure to ensure models cannot game the reward functions.
Sur place · Toronto
Design and build reinforcement learning environments and reward functions to advance model capabilities in ML research and engineering. Collaborate with researchers to develop novel approaches and implement them into production training runs.
Sur place · Toronto
The role involves training and evaluating models on proprietary RL environments to improve data quality and model capability. You will architect and optimize RL training infrastructure and design methodologies for RL agents to shorten research iteration cycles.
Sur place · Toronto
Design and scale compute, scheduling, and data infrastructure to support post-training research on RL environments. Develop core ML framework primitives and evaluation tooling to accelerate reproducible experimentation for research engineers.
Sur place · Toronto
Design and build reinforcement learning environments and reward schemes to advance model capabilities in ML research and engineering. Collaborate with a high-ownership team to develop novel approaches and implement them into production training runs.