AI Infrastructure Engineer Internship

Outcomes

• Deploy scalable LLM systems
• Operate GPU infrastructure
• Build distributed inference pipelines
• Optimize latency and throughput
• Ship production-grade AI platforms

Internship roadmap

1. 1
   LLM Systems
2. 2
   GPU Infrastructure
3. 3
   Distributed Inference
4. 4
   Vector Databases
5. 5
   Scaling + Observability
6. 6
   Production AI Platform

Curriculum timeline

• Week 1 — LLM Systems

  Foundations of inference systems and transformer serving.
  2 tasks
• Week 2 — GPU Infrastructure

  GPU scheduling, CUDA basics, and cluster design.
  0 tasks
• Week 3 — Distributed Inference

  Tensor parallelism and scalable inference serving.
  0 tasks

Task previews

Starter resources

• vLLM Documentationdoc
• Ray Serve Docsdoc

FAQ