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

About the role

TikTok is an international short video platform available in over 150 countries and regions, dedicated to inspiring creativity and bringing joy. We are building the inference infrastructure for ultra-large-scale language models, vision-language models, and frontier multimodal AI systems. Our mission is to provide a robust, scalable, and high-performance foundation for distributed serving, heterogeneous scheduling, and low-latency inference at massive scale. As a PhD intern, you will work on challenging problems in large-model online serving, including traffic orchestration, throughput and latency optimization, kernel efficiency, and production reliability for next-generation AI systems.

Our dynamic internship experience blends hands-on learning, community-building, professional development, and collaboration with industry experts.

Responsibilities

• Build and evolve next-generation inference systems for large-scale online traffic, including global scheduling across heterogeneous compute resources, high-concurrency load balancing, and efficient batch formation.
• Optimize distributed inference for 200B+ models and complex multimodal models through TP, EP, DP, and related strategies to improve throughput and latency in production.
• Develop high-performance kernels for frontier model architectures such as MoE, emerging attention mechanisms, and multimodal fusion layers using CUDA, Triton, and related tools.
• Explore AI-driven infrastructure for inference systems, including AI Agents for kernel optimization, performance tuning, consistency validation, deployment pipelines, and intelligent operations.

Requirements

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

Preferred Qualifications

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

Benefits

• Day one access to health insurance, life insurance, and wellbeing benefits.
• 10 paid holidays per year and paid sick time (56 hours if hired in the first half of the year, 40 if hired in the second half).
• Eligibility for housing allowance (for interns not working 100% remote).

Pay

The hourly rate range for this internship position is $60 per hour.