GPU-Optimized AI Infrastructure Engineer

TikTok; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

TikTok Singapore is seeking graduates to join the Live Recommendation Architecture team, developing scalable GPU-enabled systems for live video recommendations. You will optimize performance, memory usage, and data flow, collaborating with ML engineers to deliver reliable, scalable services.

Ideal candidates bring C++/CUDA/Python skills, familiarity with distributed training, and a proactive, ownership-driven mindset in a fast-moving, globally distributed team.

Qualifications

• Bachelor's or Master's degree in AI, Computer Science, or related field.
• Solid programming skills in C++/CUDA/Trition/Python.
• Familiarity with GPU architecture and distributed training.
• Experience in C/C++, Java or Golang.
• Good communication and sense of ownership and drive.

Responsibilities

• Optimize model performance and memory efficiency on GPU-based systems for TikTok Live recommendation scenarios.
• Deploy and scale high-throughput training and inference pipelines for live broadcast recommendation models.
• Develop tools, libraries, and compiler optimizations to accelerate deep learning workloads for live streaming use cases.
• Analyze system performance through GPU profiling, kernel analysis, and throughput tuning for real-time workloads.
• Build and maintain high-performance computing frameworks and storage systems for live recommendation model training and inference.

Skills

C++

CUDA

Python

Golang

Java

GPU architecture

Distributed training

Communication skills

Education

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

Tools

TVM

LLVM

NCCL

Horovod

DeepSpeed

FSDP

Job description

TikTok Singapore is seeking graduates to join the Live Recommendation Architecture team, developing scalable GPU-enabled systems for live video recommendations. You will optimize performance, memory usage, and data flow, collaborating with ML engineers to deliver reliable, scalable services.

Ideal candidates bring C++/CUDA/Python skills, familiarity with distributed training, and a proactive, ownership-driven mindset in a fast-moving, globally distributed team.