Join a small applied research team working directly with frontier AI research labs on challenging post-training problems. This research-first role focuses on reinforcement learning, training data, and experiments that help improve model capabilities.
Work with customer research teams to turn open-ended goals into concrete environments, datasets, experiments, and deliverables.
Design and run post-training workflows, including reinforcement learning methods such as GRPO, preference optimization, and supervised fine-tuning.
Evaluate which training signals improve model performance and shape high-quality trajectories and datasets with attention to correctness and edge cases.
Build reward functions, rubrics, validators, and evaluation harnesses that resist reward hacking and measure meaningful capability gains.
Analyze post-training signals and experiment results across distributed GPU clusters to determine next steps.
At least 2 years of experience as an applied researcher or research scientist in AI or machine learning research.
Hands-on model training and reinforcement learning experience from a frontier AI lab, newer AI lab, AI data lab, or a substantial independent project.
Alternatively, a strong research publication or released model with results on a notable benchmark.
Deep understanding of reinforcement learning and training data. This is not a general machine learning engineering role without RL experience.
Experience with Python, PyTorch, FSDP, FastAPI, GRPO, and distributed GPU clusters.
Experience at a frontier AI lab is valuable, and a PhD involving RL research is a plus.
Base salary is $300,000 to $500,000 annually. Visa sponsorship is available.
Hybrid role based in New York, New York, United States.