Applied RL Scientist, Post-Training & Data Signals

Nxt Level; Seattle (WA); On-site; USD 180,000 - 240,000; Full time

Job summary

Nxt Level in Seattle is seeking an Applied Researcher, Post-Training to collaborate with customer research labs and translate ambiguous goals into concrete experiments and deliverables. This is a hands-on, research-first role focused on reinforcement learning, data quality, and training signals.

The position involves designing and running post-training loops, building reward functions and evaluation harnesses, and identifying signals that truly improve model capability.

Qualifications

• Deep hands-on experience with reinforcement learning or post-training.
• Strong understanding of training data quality and how data impacts model behavior.
• Experience running or contributing to real post-training experiments.
• Experience with reinforcement learning methods such as GRPO, RLHF, or reward modeling.

Responsibilities

• Work directly with customer research labs to understand post-training problems.
• Turn unclear goals into concrete environments, datasets, experiments, and deliverables.
• Design and run post-training loops, including reinforcement learning and reward signals.
• Inspect high-fidelity trajectories and training data for quality and usefulness.
• Build reward functions, evaluators, and harnesses to measure progress.

Skills

Reinforcement learning

Post-training

Experiment design

Data quality

Research communication

Tools

GRPO

RLHF

SFT

Job description

Nxt Level in Seattle is seeking an Applied Researcher, Post-Training to collaborate with customer research labs and translate ambiguous goals into concrete experiments and deliverables. This is a hands-on, research-first role focused on reinforcement learning, data quality, and training signals.

The position involves designing and running post-training loops, building reward functions and evaluation harnesses, and identifying signals that truly improve model capability.