About the role#
This internship focuses on building infrastructure for ultra-large-scale language models and multimodal AI systems. You will work on distributed serving, heterogeneous scheduling, and low-latency inference. The role involves solving problems in traffic orchestration, kernel efficiency, and production reliability for AI systems.
What you'll do#
- Build and evolve inference systems for large-scale online traffic including global scheduling, load balancing, and batch formation.
- Optimize distributed inference for 200B+ models and complex multimodal models to improve throughput and latency.
- Develop high-performance kernels for frontier model architectures like MoE and attention mechanisms using CUDA and Triton.
- Explore AI-driven infrastructure for inference, including AI agents for performance tuning, deployment pipelines, and intelligent operations.
What you'll need#
- Currently pursuing a PhD in Computer Science, Computer Engineering, Software Development, or a related technical field.
- Familiarity with large-model architectures and system design for high-concurrency environments.
- Engineering skills in performance optimization and production system development.
- Understanding of asynchronous scheduling, resource pooling, and load balancing in distributed microservice systems.
Location & details#
- Location: San Jose, California.
- Type: Full-time internship.
- Compensation: $60 per hour.
- Term: Rolling basis.
About TikTok
TikTok operates as an entertainment provider. The company maintains a global presence with offices in cities including Los Angeles, Singapore, New York, London, and Tokyo. It employs over 92,000 people. The organization is privately held.
How to get in at TikTok
Landing an internship at TikTok requires speed because early applicants often get seen before the pile grows. Intern Insider sends an instant alert the moment a role matching your target is published anywhere, so you can apply among the first. This gives you a better chance of your resume being reviewed while the team is still actively filling the position. You should aim to be one of the first people to submit your materials. Reaching out to the right person can also improve your chances of getting a response. Intern Insider surfaces the recruiters behind the company roles so you can contact them directly to ask about the role or a referral. This direct approach often works better than waiting for a response from a general application queue.
