RL Environments Research Engineer — Frontier ML & Systems

Preference Model; San Francisco (CA); On-site; USD 170,000 - 260,000; Full time

Benefits offered by this job

Cash & equity compensation

Ownership & autonomy

Top ML engineers

Healthcare benefits

401K match

Lunch onsite

Weekly snacks

Visa sponsorship

Job summary

Preference Model is a superintelligence data research company focused on RL environments for training capable, better-aligned AIs. We hire experienced Machine Learning Engineers to design and build reinforcement learning environments for frontier models.

This role blends research and engineering with full ownership of your environments, including experiments, production training runs, and collaboration with researchers and engineers within our Capabilities org.

Qualifications

• 5+ years of experience in machine learning or research, focusing on LLMs and transformers.
• Strong ML fundamentals with broad research interests and ability to translate into RLVR problems.
• Proficiency in Python and systems programming; at least one of PyTorch or JAX.
• Problem solvers who take ownership and drive solutions end-to-end.
• Passion for staying current with evolving ML infrastructure; meet throughput expectations.

Responsibilities

• Design and build RL environments and reward functions for frontier models.
• Develop deep expertise across ML research, training, and inference infrastructure.
• Collaborate with teammates to brainstorm and create new ideas and tools for environment building.

Skills

5+ years experience

ML fundamentals

Python

Systems programming

PyTorch / JAX

Ownership & end-to-end delivery

ML infrastructure

Throughput & feedback

Education

PhD

MS

Tools

PyTorch

JAX

CUDA

Triton

Pallas

Job description

Preference Model is a superintelligence data research company focused on RL environments for training capable, better-aligned AIs. We hire experienced Machine Learning Engineers to design and build reinforcement learning environments for frontier models.

This role blends research and engineering with full ownership of your environments, including experiments, production training runs, and collaboration with researchers and engineers within our Capabilities org.