Senior ML Engineer - RL Environments for Frontier Models

Preference Model, Inc.; San Francisco (CA); On-site; USD 180,000 - 260,000; Full time

Benefits offered by this job

Competitive cash and equity

Ownership and autonomy

Work with top ML engineers

Health, vision, dental, benefits

401K match

Lunch onsite

Weekly snack orders

Visa sponsorship & relocation support

Job summary

Preference Model, Inc. is hiring experienced Machine Learning Engineers to design and build reinforcement learning environments for frontier models. You will teach frontier models to perform the work of ML engineers within a frontier lab.

This role blends research and engineering, requiring you to stay up to date with the latest research, develop novel approaches, and realize them in code. You will have full ownership of the environments you build and deploy them into production training runs,

Qualifications

• 5+ years of experience in ML or research focused on LLMs and transformer models.
• Strong ML fundamentals and ability to translate research into RLVR problems.
• Proficiency in Python and systems programming; knowledge of PyTorch or JAX.
• Ownership mindset and end-to-end delivery capability.
• Keeps up with evolving ML infrastructure.

Responsibilities

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

Skills

Python

Systems programming

LLMs / Transformer models

Problem solving

Throughput awareness

Tools

PyTorch

JAX

Job description

Preference Model, Inc. is hiring experienced Machine Learning Engineers to design and build reinforcement learning environments for frontier models. You will teach frontier models to perform the work of ML engineers within a frontier lab.

This role blends research and engineering, requiring you to stay up to date with the latest research, develop novel approaches, and realize them in code. You will have full ownership of the environments you build and deploy them into production training runs,