Research Engineer: Post-Training Data & RL Environments

NxT Level; San Francisco (CA); On-site; USD 140,000 - 230,000; Full time

Job summary

NxT Level is seeking a Research Engineer, Post-Training Data to own the full lifecycle of post-training model and data work. You will blend AI research, ML engineering, software engineering, and data production to build environments and data-generation systems for frontier AI workflows.

The role emphasizes research horsepower, strong software ability, and data-driven judgment to create scalable data infrastructure and evaluation environments for advanced AI systems.

Qualifications

• Experience in ML research or technical research domains.
• Strong software engineering ability and track record with production-quality tools or research systems.
• Ability to post-train models and build or curate high-quality post-training data.

Responsibilities

• Own post-training workflows end to end, from infrastructure provisioning through data generation and curation.
• Build and curate high-quality post-training data from model and environment generation processes.
• Produce RL environments and long-horizon tasks across complex domains.
• Debug ML pipelines, understand unfamiliar code quickly, and solve open-ended technical problems.
• Help define standards for high-quality post-training data across domains.

Skills

ML research

Software engineering

Code comprehension

PyTorch

Research tooling

Tools

PyTorch

Job description

NxT Level is seeking a Research Engineer, Post-Training Data to own the full lifecycle of post-training model and data work. You will blend AI research, ML engineering, software engineering, and data production to build environments and data-generation systems for frontier AI workflows.

The role emphasizes research horsepower, strong software ability, and data-driven judgment to create scalable data infrastructure and evaluation environments for advanced AI systems.