Open role
Member of Technical Staff - Research Engineer, RL Environments
Preference Model
About this role
Preference Model is seeking experienced Machine Learning Engineers to design and build reinforcement learning environments for training advanced AI models. In this role, you will research and implement novel approaches to shape AI behavior, contributing directly to the data layer that powers frontier LLM capabilities. You will have full ownership of the environments you build, from design and implementation to production deployment.
What we are looking for 6
- Design and build RL environments and reward functions for frontier models
- Develop deep expertise in ML research, training, and inference infrastructure
- Collaborate on new ideas and tools for environment building
- 5+ years of experience in ML/research, primarily on LLMs and transformers
- Strong ML fundamentals and creativity to translate research into RL problems
- Proficiency in Python, systems programming, and PyTorch or JAX