remote
Member of Technical Staff, Research Engineering - micro1
Software Engineer
Senior research engineer focused on building reinforcement learning systems, designing data pipelines, and creating scalable RL environments to train and evaluate AI agents across diverse domains.
About the role
Key Responsibilities
- Design, implement, and optimize reinforcement learning algorithms and workflows for large‑scale AI training.
- Develop and maintain high‑quality data pipelines that transform domain expertise into structured training datasets.
- Build and extend RL environments that simulate real‑world scenarios for agent evaluation.
- Collaborate with cross‑functional teams to integrate feedback loops and improve model performance.
- Document research findings and contribute to open‑source tooling and internal knowledge bases.
Requirements
- Advanced expertise in reinforcement learning and machine learning principles.
- Proficiency in data design, pipeline engineering, and environment construction.
- Experience with scalable RL workflows and production‑grade deployment.
- Strong analytical skills and ability to translate complex domain knowledge into actionable data.
- Excellent communication and collaboration skills in a fast‑moving research setting.
Skills
reinforcement learningmachine learning