Member of Technical Staff - Research Engineer, RL Environments

Preference Model•San Francisco, CA

4d•$200,000 - $350,000

About The Position

Preference Model is hiring an experienced Machine Learning Engineer to design and build reinforcement learning environments that safely advance model capabilities in machine learning research and engineering. The role focuses on teaching frontier models to perform work similar to that of an ML engineer or researcher at a frontier lab. This position blends research and engineering. The engineer will stay current with research, develop new approaches, and implement them in code, with ownership and autonomy over the environments they build. Work includes designing and implementing RL environments, running experiments and evaluations, delivering work into production training runs, and collaborating with researchers and engineers. The role is part of the Capabilities organization, a small, high-ownership team contributing to the data layer that powers frontier LLM capability. It is intended for experienced ML engineers; the company has a separate opening for new graduates.

Requirements

At least 5 years of experience working in machine learning or research, primarily on LLMs and transformer models.
Strong machine learning fundamentals and broad research interests.
Ability to read and deeply understand papers or tutorials and translate their ideas into RLVR problems.
Proficiency in Python and systems programming.
Proficiency in at least one of PyTorch or JAX.
Ability to take ownership and drive solutions end-to-end.
Passion for staying current with the rapidly evolving ML infrastructure landscape.
Ability to meet throughput expectations and respond quickly to feedback.

Nice To Haves

Expert knowledge in an active deep learning or machine learning research area, with publications or public code demonstrating expertise.
Research experience, such as a PhD or MS.
Deep understanding of transformer internals and training or inference of modern LLMs.
Experience with inference libraries such as vLLM or SGLang.
Strong expertise in kernel development, including CUDA, Triton, or Pallas.
Experience building complex interactive RL environments.

Responsibilities

Design and build RL environments and reward functions that produce clean, learnable signals for frontier models on ML research and engineering tasks.
Build deep expertise across frontier ML research, training, and inference infrastructure.
Collaborate with others to brainstorm and create ideas and tools that improve the environment-building process.
Conduct experiments and evaluations, and deliver work into production training runs.