PhD Intern: High-Performance Distributed ML Systems

TikTok; Singapore; On-site; SGD 17,000 - 23,000; Part time

Job summary

TikTok is offering a PhD internship focused on distributed training and inference optimization for large-scale recommendation models and LLMs. You will work on GPU kernel design and high-performance architectures, collaborating with cross-functional teams to translate research into production impact.

The role emphasizes publishing research findings and contributing to platform stability and efficiency while gaining hands-on experience in a leading tech company.

Qualifications

• Currently pursuing a PhD in Computer Science, engineering or quantitative field.
• Strong programming skills in C++/CUDA/Python, with solid understanding of deep learning frameworks (PyTorch/TensorFlow).
• Published research in systems, machine learning, or related areas at top conferences.

Responsibilities

• Conduct novel research on distributed training and inference system optimization for large-scale recommendation models and LLMs.
• Design and implement high-performance GPU kernel architectures and communication primitives to accelerate deep learning workloads.
• Publish original research findings at top-tier conferences and collaborate with cross-functional teams to translate research into production impact.

Skills

PhD candidate

C++/CUDA/Python

Deep learning frameworks

Distributed training

Education

PhD candidate in CS/engineering

Tools

PyTorch

TensorFlow

DeepSpeed/FSDP

Megatron-LM

Job description

TikTok is offering a PhD internship focused on distributed training and inference optimization for large-scale recommendation models and LLMs. You will work on GPU kernel design and high-performance architectures, collaborating with cross-functional teams to translate research into production impact.

The role emphasizes publishing research findings and contributing to platform stability and efficiency while gaining hands-on experience in a leading tech company.