Research Intern (Inference Infrastructure) - 2027 Start (PhD)

What you'll do

• Design and build scalable, resilient container-based cluster management and orchestration systems.
• Architect cloud-native GPU and AI accelerator infrastructure for cost-efficient, secure ML platforms.
• Collaborate on LLM inference solutions and write production-ready code.

What they ask for

• Currently pursuing a PhD in Computer Science or a related discipline; the posting also mentions related fields with 2+ years of relevant experience and PhD candidates with strong systems/ML publications.
• Able to commit to 12 weeks during Summer 2027.
• Strong understanding of large model inference, distributed and parallel systems, and/or high-performance networking systems; hands-on experience building cloud or ML infrastructure.
• Knowledge of Docker and Kubernetes, and proficiency in at least one of Go, Rust, Python, or C++.

Nice to have

• Experience with large-scale cluster management, workload scheduling, GPU orchestration, scaling, or isolation.
• Hands-on GPU programming or inference-engine experience; familiarity with cloud ML platforms and distributed ML systems.

Tools

vLLM, SGLang, TensorRT-LLM, Kubernetes, Ray, Docker, Go, Rust

AI focus

Develop infrastructure for LLM inference, GPU and AI accelerator workloads, and ML platforms.