Research Engineer - Reinforcement Learning
Core
Design and implement end-to-end pipelines for synthetic data generation and orchestration to support large-scale AI model training and inference.
Role type
Senior IC research engineer (reinforcement learning & synthetic data)
Builds
Open-source libraries, distributed RL frameworks, and a full-stack platform for post-training frontier AI models.
Domain
Frontier AI, Reinforcement Learning, Synthetic Data Generation, AI Infrastructure
Deliverable
production ML models
Required skills
Distributed inference techniques, MLOps, Large-scale AI model training pipelines, Compute & memory optimization, Open-source framework development
Preferred skills
Publishing in top-tier AI conferences, Technical writing for layman audiences
Technologies
vllm, sglang
Responsibilities
Lead research for synthetic data generation pipelines, Optimize AI inference workloads for performance and cost, Contribute to open-source distributed RL frameworks, Publish research at ICML/NeurIPS, Write technical blogs distilling project outcomes
Seniority
Senior, hands-on IC