T

TikTok

Short-form video platform with ads

AI Infra Optimization Engineer Graduate - Global E-Commerce Recommendation & Search Architecture

Applied Machine LearningConfirmed live in the last 24 hours
Full-timeSingaporeNo salary listedIn-person

About the Job

Requirements

  • Individuals must be completing or have recently completed a Bachelor's or Master's degree in Artificial Intelligence, Software Development, Computer Science, Computer Engineering, or a related discipline.
  • Have solid programming skills in C++, CUDA, Triton, or Python.
  • Have experience programming in at least one of C, C++, Java, or Golang.
  • Have effective communication skills and a sense of ownership and drive.

Responsibilities

  • Develop, deploy, and optimize large language model training and inference techniques for recommendation foundation models, and solve large-model engineering challenges in recommendation scenarios.
  • Provide highly automated, agentic, and performance-oriented model optimization solutions for frameworks such as PyTorch.
  • Build, design, and implement next-generation model infrastructure architectures based on open-source components such as vLLM, SGLang, Megatron, and VeRL, enabling recommendation foundation models to be deployed in production.
  • Co-design with algorithm teams to research, innovate, and productionize end-to-end generative recommendation technologies.
  • Re-architect recommendation models and the complete training and inference technology stack through secondary development based on PyTorch and large language model components.
  • Develop ultra-long-context modeling of users' lifelong behavioral histories.
  • Enable key-value cache sharing across multiple user browsing sessions.
  • Develop multimodal recommendation foundation models and downstream fine-tuning tasks.
  • Optimize throughput for high-performance GPU kernels and multi-GPU parallelism.
  • Optimize performance for the specialized structures of recommendation models.
  • Explore agentic paradigms for performance optimization and new AI infrastructure paradigms enabled by AI-powered productivity.
  • Develop shared modeling and shared computation across retrieval, pre-ranking, ranking, and re-ranking stages.
  • Develop prefill/decode disaggregation and computation graph partitioning tailored to recommendation workloads.
  • Develop large language model architectures that support the sparse characteristics of recommendation scenarios.
  • Align multimodal large language model foundations with recommendation tasks.
  • Implement, deploy, and optimize reinforcement learning techniques in recommendation scenarios.
  • Construct data and samples for generative recommendation.
  • Explore new recommendation paradigms and technical approaches.

Desired Qualifications

  • Familiarity with GPU architecture and distributed training is highly desirable.
  • Have strong programming and algorithmic foundations, with proficiency in languages such as C/C++ and Python.
  • Have experience with CUDA development and familiarity with TensorRT, Triton, or CUTLASS.
  • Be familiar with research and technical developments in large language model inference acceleration, including model quantization, graph compilation, operator optimization, key-value cache optimization, and prefill/decode disaggregation.
  • Have hands-on knowledge of large language model training and inference technologies, with practical development and production experience using systems such as Megatron-LM, DeepSpeed, vLLM, SGLang, or TensorRT-LLM.
  • Have extensive experience and broad technical perspective in foundation model engineering, close awareness of open-source developments, and strong independent troubleshooting capabilities.
  • Experience in recommendation, advertising, or search model development and optimization, or contributions to open-source foundation model communities, is a plus.

About the Company

TikTok

Short-form video platform with ads

TikTok is a short-form mobile video platform that lets people create, discover, and share quick videos. Users upload vertical clips, edit them with built-in tools, and browse a personalized feed powered by an algorithm that highlights relevant content. Advertisers can use in-feed ads, branded hashtags, and the Business Center to plan and measure campaigns, making it easy for brands to reach a global audience. Its goal is to inspire creativity and bring joy by helping people express themselves and by connecting brands with a wide audience.

Company size
10,001+
Company stage
Grant
Total funding
$740K
Headquarters
Santa Monica, CA
Founded
2016

Recently Posted Jobs

Explore more opportunities at TikTok

See more jobs