AI Infrastructure Engineer Intern: Large-Scale Inference

TikTok; San Jose (CA); On-site; USD 70,000 - 95,000; Full time

Benefits offered by this job

Health insurance

Housing allowance

Paid holidays

Job summary

TikTok is seeking an AI Infrastructure Engineer Intern (Algorithm Infrastructure) for a 2027 start in San Jose. You will contribute to building and optimizing ultra-large-scale inference systems, focusing on throughput, latency, and reliability for next-generation AI models.

The role targets PhD students in related fields, offering hands-on experience with distributed serving, kernel optimization, and AI-driven infrastructure within a globally-dispersed team.

Qualifications

• Pursuing a PhD in Computer Science, Software Engineering, AI, Math, or related field.
• Familiarity with large-model architectures and high-concurrency systems.
• Strong engineering skills in performance optimization and production systems.
• Knowledge of asynchronous scheduling, resource pooling, and load balancing in distributed microservices.

Responsibilities

• Build and evolve next-generation inference systems for large-scale online traffic and global scheduling across heterogeneous compute resources.
• Optimize distributed inference for 200B+ models and complex multimodal models to improve throughput and latency in production.
• Develop high-performance kernels for frontier model architectures using CUDA, Triton, and related tools.
• Explore AI-driven infrastructure for inference systems, including AI Agents for kernel optimization and deployment pipelines.

Skills

Large-model inference

System design

Performance optimization

Education

PhD candidate in CS/related field

Tools

CUDA

Triton

C++

Job description

TikTok is seeking an AI Infrastructure Engineer Intern (Algorithm Infrastructure) for a 2027 start in San Jose. You will contribute to building and optimizing ultra-large-scale inference systems, focusing on throughput, latency, and reliability for next-generation AI models.

The role targets PhD students in related fields, offering hands-on experience with distributed serving, kernel optimization, and AI-driven infrastructure within a globally-dispersed team.