Quick overview
Job description
About the Role
Join an applied research team working with advanced AI research organizations on challenging post-training problems. This research-first role focuses on reinforcement learning, training data, and experiments that improve model capabilities.
What You'll Do
Work with research teams to translate open-ended goals into environments, datasets, experiments, and deliverables.
Design and run post-training workflows, including reinforcement learning methods such as GRPO, preference optimization, and supervised fine-tuning.
Shape and inspect high-quality trajectories and training data, with attention to correctness, edge cases, and quality.
Build reward functions, rubrics, validators, and evaluation harnesses that resist reward hacking and measure capability gains.
Analyze training signals and experiment results across distributed GPU clusters to guide follow-up experiments.
What We're Looking For
At least 2 years of experience as an applied researcher or research scientist.
Hands-on model training experience in an AI research lab, AI data organization, or comparable setting, or a strong research or model release record on a recognized benchmark.
Practical reinforcement learning and agent experience beyond typical machine learning engineering work.
Experience with Python, PyTorch, FSDP, FastAPI, GRPO, and distributed GPU clusters.
Experience at an advanced AI research organization or a PhD involving reinforcement learning research is relevant.
Compensation & Benefits
Base salary: $300,000 to $500,000 annually. Visa sponsorship is available.
Location
Hybrid, based in New York, New York. Seattle is also listed as a location.