Tech Expert/Backend Engineer - Global Live (LLM Model Serving)
TIKTOK PTE. LTD.
Singapore
**
Deploy large-scale deep learning models
Optimize model inference performance
Proficiency in python c++ or golang
**
TikTok is seeking a Tech Expert/Backend Engineer for its Global Live team in Singapore, focusing on deploying and optimizing large-scale machine learning models for live streaming. The ideal candidate will possess experience in deep learning frameworks and model optimization techniques, contributing to TikTok's mission of inspiring creativity and bringing joy.
**
Job Summary
The role involves converting large-scale deep learning models into scalable services for TikTok's live streaming business.
Engineers will optimize model inference to ensure efficient resource utilization, minimal response time, and maximum throughput.
Candidates must collaborate closely with algorithm and business teams to deploy models into production environments.
Matching Summary
Match Score: 75
**
TikTok is seeking a Tech Expert/Backend Engineer for its Global Live team in Singapore, focusing on deploying and optimizing large-scale machine learning models for live streaming. The ideal candidate will possess experience in deep learning frameworks and model optimization techniques, contributing to TikTok's mission of inspiring creativity and bringing joy.
**
Skills & Requirements
Must-have
Deploy large-scale deep learning models
Optimize model inference performance
Proficiency in Python C++ or Golang
Experience with TensorFlow PyTorch DeepSpeed
Knowledge of RPC Redis Kafka stacks
Nice-to-have
LLM deployment and optimization experience
Model quantization and distillation techniques
Distributed inference and ONNX expertise
ZeRO optimization methods familiarity
Cross-team collaboration skills
Key Requirements
Bachelor's degree in Computer Science or related field
3+ years of experience deploying ML models
Deep understanding of system performance optimization