Research and build efficient ML systems for large-scale LLMs and agentic RL: design algorithms and system techniques, prototype in training/inference stacks, run large-scale experiments, and translate findings into production or publications.

Design, build, and operate end-to-end training and inference infrastructure for large language and multimodal models. Improve efficiency (memory, parallelism, kernel optimizations), ensure robust scalable training and RL pipelines, optimize low-latency/high-throughput serving (quantization, caching, speculative decoding), manage multi-GPU and multi-cloud orchestration, and productionize new algorithms with strong observability and reproducibility.