Member of Technical Staff, ML Capabilities

Preference Model•San Francisco, CA

22h•Onsite

About The Position

Preference Model is building automated ML research engineering. Existing frontier models are brittle when applied to real-world ML tasks. The present bottleneck is the lack of high-quality RL training environments. Our first step is to build RL environments that reflect real-world complexity, with diverse tasks and robust reward functions. Our founding team has previous experience on Anthropic’s data team building data infrastructure, and datasets behind Claude. We are partnering with leading AI labs to push AI closer to achieving its transformative potential. We’re hiring experienced ML Engineers to design and build reinforcement learning environments to safely advance model capabilities specifically on machine learning research and engineering tasks to do the work of an MLE at a frontier lab. This role blends research and engineering. It will require you to both develop novel approaches and realize them in code. Your work will include designing and implementing RL environments, conducting experiments and evaluations, delivering your work into production training runs, and collaborating with other researchers and engineers. You will join our ML Capabilities org, a small, high-ownership team and contribute directly to the data layer that powers frontier LLM capability. Note: This role is only for experienced ML Engineers. We have separate openings for New Grads, and for Interns.

Requirements

Strong ML fundamentals and broad research interests.
Ability to read many papers or tutorials, understand topics deeply and have the creativity to translate them into RLVR problems.
Proficiency in Python and systems programming.
At least one of PyTorch or JAX.
Problem solvers who take ownership and drives 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.
Expert knowledge in an active DL/ML research area, with publications or public code to show for it.
Deep understanding of transformer internals, training/inference of modern LLMs.
Experience with inference libraries (vLLM, SGLang, etc).
Strong expertise in kernel development (CUDA, Triton, Pallas).
You have built complex interactive RL environments.

Nice To Haves

Research experience (PhD, MS) is a big plus.

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 the frontier of ML research, training, and inference infrastructure.
Collaborate with others to brainstorm and create new ideas and tools to improve the environment building process.
Designing and implementing RL environments.
Conducting experiments and evaluations.
Delivering your work into production training runs.
Collaborating with other researchers and engineers.