Tech Expert/Backend Engineer - Global Live (LLM Model Serving)
TIKTOK PTE. LTD.
Singapore, Singapore
Not specified; not specified; not specified
Not specified (assumed to be hybrid based on industry norms).
3+ years deploying large-scale ml models
Proficiency in tensorflow or pytorch
Experience with model inference optimization
TikTok is seeking a Tech Expert/Backend Engineer for their Global Live (LLM Model Serving) team in Singapore. The role focuses on deploying and optimizing large-scale deep learning models for TikTok's live streaming services, requiring strong technical skills and collaborative abilities
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 performance to minimize response time and maximize throughput while utilizing computing resources efficiently.
Candidates must collaborate closely with algorithm and business teams to facilitate production deployments and resolve issues.
Matching Summary
Match Score: 85
TikTok is seeking a Tech Expert/Backend Engineer for their Global Live (LLM Model Serving) team in Singapore. The role focuses on deploying and optimizing large-scale deep learning models for TikTok's live streaming services, requiring strong technical skills and collaborative abilities.
Salary
Not specified; Not specified; Not specified
Skills & Requirements
Must-have
3+ years deploying large-scale ML models
Proficiency in TensorFlow or PyTorch
Experience with model inference optimization
Strong Python, C++, or Golang skills
Familiarity with RPC, Redis, Kafka
Nice-to-have
LLM deployment and optimization experience
Knowledge of quantization and distillation
Experience with distributed inference
Understanding of ONNX and ZeRO
Curiosity and humility mindset
Key Requirements
Bachelor's degree in Computer Science or related field