LLM Infra Optimization Engineer — Generative Recs & GPU

TikTok; Singapore; On-site; SGD 60,000 - 100,000; Full time

Job summary

TikTok is hiring graduates for its E-commerce Recommendation Infra team in Singapore. You will work on integrating LLMs with large-scale recommender systems, developing training and inference optimizations, and building production-ready model infrastructure using open-source components.

Successful candidates should be nearing completion of a Bachelor's or Master's degree in AI/CS/Engineering and demonstrate strong programming in C++, CUDA, Triton, and Python, plus experience with distributed

Qualifications

• Bachelor's or Master's in AI/CS/Engineering or related field.
• Solid programming skills in C++/CUDA/Triton/Python.
• Familiarity with GPU architecture and distributed training is desirable.
• Experience in languages: C, C++, Java or Golang.
• Strong communication and ownership skills.

Responsibilities

• Deeply integrate LLM and recommendation technologies; develop, deploy, and optimize LLM training and inference techniques for recommendation foundation models.
• Provide automated, performance-oriented model optimization solutions for frameworks such as PyTorch.
• Build and implement next-generation model infra architectures using open-source components to productionize recommendation models.
• Co-design with algorithm teams to research, innovate, and productionize end-to-end generative recommendation technologies.
• Advance research areas: LLM-native models, training/inference architectures, and multi-modal foundations.
• Explore and optimize end-to-end generative recommendation and reinforcement learning techniques.

Skills

C++

CUDA

Triton

Python

Golang

Java

Communication

Education

Bachelor's or Master's in AI/CS/Engineering

Tools

Megatron-LM

DeepSpeed

vLLM

SGLang

TensorRT-LLM

Job description

TikTok is hiring graduates for its E-commerce Recommendation Infra team in Singapore. You will work on integrating LLMs with large-scale recommender systems, developing training and inference optimizations, and building production-ready model infrastructure using open-source components.

Successful candidates should be nearing completion of a Bachelor's or Master's degree in AI/CS/Engineering and demonstrate strong programming in C++, CUDA, Triton, and Python, plus experience with distributed