Research Engineer/Research Scientist in Reinforcement Learning for Superintelligence Training

preference model • United State

Visa Sponsorship Relocation

Apply Now

AI Summary

Join Preference Model to advance RL environments for training future superintelligent models. You’ll design, optimize, and scale training pipelines, evaluate models, and push the boundaries of self-directed learning in large language models. Requires expertise in end-to-end LLM post-training, Python, and modern RL frameworks.

Key Highlights

Research and engineering role focused on RL environments for superintelligent models

Build and optimize scalable ML infrastructure for large-scale training pipelines (7B+ models)

Collaborate on cutting-edge post-training methodologies with minimal formal ML training required

Key Responsibilities

Train and evaluate models on proprietary RL environments to validate data quality and improve task coverage

Design, implement, and optimize RL training infrastructure, including distributed experiment management

Profile and optimize end-to-end training pipelines to maximize throughput and accelerate research iteration

Looking to advance your Development & Programming career with relocation support? Explore Development & Programming Jobs with Relocation Packages that include comprehensive packages to help you move and settle in your new role.

Technical Skills Required

Python PyTorch Reinforcement Learning (RL)

Benefits & Perks

Competitive cash and equity compensation (>90th percentile)

Health, vision, dental, and 401K benefits

Visa sponsorship and relocation support available

Discover our full range of relocation jobs with comprehensive support packages to help you relocate and settle in your new location.

Nice to Have

Experience evaluating model outputs and building reward/evaluation signals

Strong systems design and communication skills for startup research

Current knowledge of post-training research and ability to translate papers into code

Job Description

Preference Model is a superintelligence data research company. We build RL environments for training capable, better-aligned superintelligences.Almost every aspect of how a model behaves is shaped by the reward signals it's trained on. The biggest problem with AIs today is that they don't always do what we intend. Sometimes that's because they aren't capable enough, and sometimes it's because they aren't aligned. Both problems come down to the training objectives.

Want the full job description? Read the complete details on LinkedIn, the original posting.

Continue on LinkedIn

This is a short excerpt. All rights to the full description belong to its original publisher.