Staff RL Researcher — Post-Training & Data Quality

true-talent-solutions-partners; New York (NY); Hybrid; USD 300,000 - 500,000; Full time

Benefits offered by this job

Visa sponsorship

Job summary

true-talent-solutions-partners is seeking an applied researcher to drive RL-based post-training improvements. You will partner with research teams to translate open-ended goals into concrete environments and experiments, and design reward systems and evaluation harnesses for robust progress.

The role emphasizes hands-on RL work, distributed GPU scaling, and evaluation across AI research pipelines in a hybrid New York setting. Visa sponsorship is available for eligible candidates.

Qualifications

• Minimum 2 years of experience as an applied researcher or in a comparable research role.
• Hands‑on model training experience in an AI research lab, newer AI lab, or with released models that show strong benchmark results.
• Practical reinforcement learning and agent experience beyond typical ML engineering work.
• Strong experience with Python, PyTorch, FSDP, FastAPI, GRPO, and distributed GPU clusters.
• PhD involving RL research is relevant.

Responsibilities

• Partner with research teams to turn open-ended goals into concrete environments, datasets, experiments, and deliverables.
• Design and run post-training workflows using reinforcement learning methods such as GRPO, preference optimization, and supervised fine-tuning.
• Shape and inspect high-quality trajectories and training data, paying close attention to correctness, edge cases, and quality.
• Develop 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 next steps.

Skills

Reinforcement learning

Python

PyTorch

Distributed GPU clusters

Experimentation

Education

PhD in RL or related field

Tools

GRPO

FSDP

FastAPI

Job description

true-talent-solutions-partners is seeking an applied researcher to drive RL-based post-training improvements. You will partner with research teams to translate open-ended goals into concrete environments and experiments, and design reward systems and evaluation harnesses for robust progress.

The role emphasizes hands-on RL work, distributed GPU scaling, and evaluation across AI research pipelines in a hybrid New York setting. Visa sponsorship is available for eligible candidates.