Research Engineer: RL & Post-Training LLM Systems

Preference Model; San Francisco (CA); On-site; USD 120,000 - 150,000; Full time

Benefits offered by this job

Competitive cash and equity compensation (>90th percentile)

Health, vision, dental benefits

401K match

Lunch provided every day onsite

Visa sponsorship & relocation support available

Job summary

Preference Model is seeking Research Engineers or Research Scientists to advance self-directed learning in AI. The role involves training and evaluating models within proprietary RL environments and optimizing ML infrastructure.

Candidates will benefit from competitive compensation, ownership in a fast-paced startup, and support for personal growth. Experience in Python, PyTorch, or JAX, along with RL training frameworks, is desired. The opportunity is a unique blend of research and engineering within a dynamic team.

Qualifications

• Experience running end-to-end LLM post-training pipelines.
• Experience with at least one modern RL training framework.
• Experience building and operating ML infrastructure at scale.

Responsibilities

• Train and evaluate models on proprietary RL environments.
• Architect and optimize RL training infrastructure.
• Design, implement, and test training environments for RL agents.
• Profile and optimize training runs end-to-end.

Skills

Python

PyTorch

JAX

RL training

ML infrastructure

Job description

Preference Model is seeking Research Engineers or Research Scientists to advance self-directed learning in AI. The role involves training and evaluating models within proprietary RL environments and optimizing ML infrastructure.

Candidates will benefit from competitive compensation, ownership in a fast-paced startup, and support for personal growth. Experience in Python, PyTorch, or JAX, along with RL training frameworks, is desired. The opportunity is a unique blend of research and engineering within a dynamic team.