Remote Reinforcement Learning Research Engineer

Visa Hunt; United States; Remote; USD 140,000 - 180,000; Full time

Benefits offered by this job

Remote-first company

Equity compensation

Performance-based bonuses

Job summary

micro1 seeks a Member of Technical Staff, Research Engineering to push the frontier of reinforcement learning. You will design self-contained RL environments, build scalable training pipelines, and create evaluation systems that drive high-performance AI models in a remote-first setup.

You will collaborate across research and production, translating ideas into reproducible experiments and contributing to benchmarks and releases on internal platforms.

Qualifications

• Deep experience in reinforcement learning, including environment design and training dynamics.
• Proven ability to build and scale RL systems, pipelines, or experimentation frameworks.
• Experience with synthetic data pipelines and automated evaluation workflows.
• Strong communication and technical writing skills in a fast-paced research setting.

Responsibilities

• Architect self-contained RL environments with rewards, verifiers, and evaluation logic.
• Design and scale episode pipelines and training processes to support reproducible experiments.
• Build automated data generation systems using synthetic data for faster iterations.
• Develop AI-driven evaluation and QA systems for automated grading and feedback.
• Fine-tune open-source RL models using internal datasets and custom training strategies.
• Establish benchmarking frameworks to measure model capability and data quality.
• Contribute to releases and analyses of evaluations on internal benchmark platforms.

Skills

Reinforcement Learning

RL Environment Design

RL System Scaling

Automation & Data Generation

Automated Evaluation Systems

Open-Source ML Tuning

Technical Writing

Job description

micro1 seeks a Member of Technical Staff, Research Engineering to push the frontier of reinforcement learning. You will design self-contained RL environments, build scalable training pipelines, and create evaluation systems that drive high-performance AI models in a remote-first setup.

You will collaborate across research and production, translating ideas into reproducible experiments and contributing to benchmarks and releases on internal platforms.