About the role#
The Inference Infrastructure team builds and maintains AIBrix, a Kubernetes-native control plane for large-scale LLM inference. We design and operate the platforms that power machine learning training, inference, and distributed storage across global datacenters. You will join us to build cloud-native, GPU-optimized orchestration systems that support millions of containers daily. This role involves working in a large-scale environment to help bring AI workloads from research to production.
What you'll need#
- Currently pursuing a PhD in Computer Science or a related field, or possess 2+ years of relevant experience.
- Ability to commit to a 12-week internship during Summer 2027.
- Strong understanding of large model inference, distributed systems, or high-performance networking.
- Hands-on experience building cloud or ML infrastructure, including resource management, scheduling, or request routing.
- Solid knowledge of Docker and Kubernetes.
- Proficiency in at least one major programming language: Go, Rust, Python, or C++.
- Experience with large-scale cluster management systems like Kubernetes or Ray is preferred.
- Experience with GPU orchestration, workload scheduling, or isolation in production is preferred.
- Familiarity with GPU programming, inference engines, public cloud ML platforms, or ML systems like PyTorch and DeepSpeed is a plus.
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 secure and cost-efficient ML platforms.
- Collaborate with teams to deliver inference solutions using engines such as vLLM, SGLang, and TensorRT-LLM.
- Integrate best practices from systems research and open-source developments into production.
- Write maintainable, testable, and scalable code for production systems.
Location & details#
- Location: San Jose, California.
- Modality: On-site.
- Term: Summer 2027 (12 weeks).
- Employment: Full-time internship.
- Compensation: $60 per hour.


