About the role#
The Inference Infrastructure team builds and maintains AIBrix, a Kubernetes-native control plane for large-scale LLM inference. We are part of the Core Compute Infrastructure organization, which manages the platforms powering microservices, big data, distributed storage, and machine learning across global datacenters. We are looking for a PhD intern to help us design the next generation of cloud-native, GPU-optimized orchestration systems.
What you'll need#
- Currently pursuing a PhD in Computer Science, Computer Engineering, Electrical Engineering, or a related field.
- Ability to commit to a 12-week internship during Summer 2027.
- Strong understanding of large model inference, distributed systems, and high-performance networking.
- Hands-on experience building cloud or ML infrastructure, such as resource management, scheduling, request routing, or orchestration.
- Solid knowledge of Docker and Kubernetes.
- Proficiency in Go, Rust, Python, or C++.
- Experience with GPU programming (CUDA) or inference engines like vLLM, SGLang, or TensorRT-LLM.
- Familiarity with public cloud providers like AWS, Azure, or GCP and their ML platforms.
- Knowledge of ML systems such as Ray, DeepSpeed, or PyTorch.
- Experience operating large-scale cluster management systems.
What you'll do#
- Design and build large-scale, container-based cluster management and orchestration systems.
- Architect cloud-native GPU and AI accelerator infrastructure for cost-efficient and secure ML platforms.
- Work with teams to deliver inference solutions using vLLM, SGLang, TensorRT-LLM, and other LLM engines.
- Integrate advances in open source, AI/ML infrastructure, and systems research into production systems.
- Write high-quality, maintainable, testable, and scalable code.
Location & details#
- Location: Seattle, Washington, United States.
- Term: Summer 2027 (12 weeks).
- Modality: On-site.
- Employment: Full-time internship.


