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

TikTok
San Jose
InternshipFunction: DevOps, Cloud & InfrastructureEducation: phdSkills: []

Build and evolve next-generation inference infrastructure for ultra-large language and multimodal models, focusing on global scheduling, high-concurrency load balancing, and efficient batch formation. Optimize distributed inference for 200B+ models using TP/EP/DP strategies, and develop high-performance CUDA/Triton kernels for frontier architectures like MoE and multimodal fusion layers. Contribute to AI-driven infrastructure, including intelligent operations, validation, and deployment pipelines.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
TikTok
TikTok
1 day ago

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

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 12 hours agoStatus: Live

Job Summary

Build and evolve next-generation inference infrastructure for ultra-large language and multimodal models, focusing on global scheduling, high-concurrency load balancing, and efficient batch formation. Optimize distributed inference for 200B+ models using TP/EP/DP strategies, and develop high-performance CUDA/Triton kernels for frontier architectures like MoE and multimodal fusion layers. Contribute to AI-driven infrastructure, including intelligent operations, validation, and deployment pipelines.
Location: San Jose
Employment Type: Internship
Job Function: DevOps, Cloud & Infrastructure
Seniority: Graduate level

Key Responsibilities

  • •Build and evolve next-generation inference systems for large-scale online traffic, including global scheduling and efficient batch formation.
  • •Optimize distributed inference for 200B+ and complex multimodal models using TP, EP, DP 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 and Triton.
  • •Explore AI-driven infrastructure for inference systems, including AI Agents for kernel optimization, performance tuning, consistency validation, deployment pipelines, and intelligent operations.

Key Requirements

  • •Completing or recently completed a PhD in Software Development, Computer Science, Computer Engineering, or related technical disciplines (e.g., AI, Mathematics).
  • •Familiarity with large-model architectures and strong system design skills for complex, high-concurrency environments.
  • •Strong understanding of asynchronous scheduling, resource pooling, and load balancing in distributed microservice systems.
  • •Strong engineering skills in performance optimization and production system development.
Experience:Large language modelsMultimodal AIDistributed systemsOnline servingMicroservices
Education:PhD / Doctorate in Software Development, Computer Science, Computer Engineering, Artificial Intelligence, Mathematics (or related technical discipline)
Tech Stack:CUDATritonTPEPDPMoEDistributed microservice systemsAsynchronous schedulingLoad balancingResource pooling

Company Brief

TikTok
Short-form video platform that lets users create, share, and discover entertainment content through algorithmic recommendations. It also offers advertising and creator tools for brands, influencers, and businesses.
Industry: Digital Media
Company Size: Enterprise (1,001+ employees)
Growth: Scaleup
Headquarters: Singapore, Singapore
Founded: 2016
WebsiteLinkedIn