Member of Technical Staff, Applied Researcher

About the Role

Join a small applied research team working with frontier AI research groups on challenging post-training problems. This is a research-first role focused on reinforcement learning, training data, and identifying the signals that lead to meaningful model improvements.

What You'll Do

• Partner with research teams to turn open-ended goals into concrete environments, datasets, experiments, and deliverables.

• Design and run post-training loops using reinforcement learning techniques such as GRPO, preference optimization, and supervised fine-tuning.

• Shape and inspect high-fidelity trajectories and training data, with careful attention to correctness, edge cases, and quality.

• Build reward functions, rubrics, validators, and evaluation harnesses that resist reward hacking and measure real capability gains.

• Analyze post-training signals and experiment results across distributed GPU clusters to guide the next research steps.

What We're Looking For

• At least 2 years of experience as an applied researcher or research scientist.

• Hands-on model training experience in a frontier AI lab, newer AI research organization, AI data lab, or through a substantial independent project.

• Practical reinforcement learning and agent experience that goes beyond standard machine learning engineering work.

• A track record of research results, such as published work or a model performing well on a notable benchmark.

• Experience with Python, PyTorch, FSDP, FastAPI, GRPO, and distributed GPU clusters.

• Experience at a frontier AI lab or a PhD involving reinforcement learning is a plus.

Compensation & Benefits

Base salary: $300,000 to $500,000 annually. Visa sponsorship is available.

Location

Hybrid role based in New York, New York.