Drimva

TikTok

AI Infrastructure Engineer Intern (Algorithm Infrastructure) - 2027 Start (PhD)

San Jose, California · Internship · Posted Oct 28, 2026

Education
Currently pursuing a PhD in Software Development, Computer Science, Computer Engineering, or a related technical discipline in Computer Science, Software Engineering, Artificial Intelligence, Mathematics, or related fields.

About the job

Build and optimize large-scale inference infrastructure for language, vision-language, and multimodal AI systems, focusing on distributed serving, performance, and reliability.

What you'll do

  • Develop inference systems for large-scale traffic, including scheduling, load balancing, and batch formation across heterogeneous compute resources.
  • Optimize distributed inference for 200B+ and multimodal models to improve production throughput and latency.
  • Develop high-performance kernels and explore AI-driven tools for optimization, validation, deployment, and operations.

What they ask for

  • Currently pursuing a PhD in a relevant technical discipline or related field.
  • Familiarity with large-model architectures and strong system design skills for complex, high-concurrency environments.
  • Strong engineering skills in performance optimization and production system development.

Nice to have

  • Strong understanding of asynchronous scheduling, resource pooling, and load balancing in distributed microservice systems.

Tools

CUDA, Triton, TP, EP, DP

AI focus

Develop inference infrastructure for large-scale language, vision-language, and multimodal AI systems; explore AI agents for kernel optimization, performance tuning, consistency validation, deployment pipelines, and intelligent operations.

Model-written summary · the original posting is authoritative

First seen Oct 28, 2026 · Last verified Nov 5, 2026 (UTC)