AI Infra Engineer: Scalable LLM & GPU Systems

TikTok; San Jose (CA); On-site; USD 128,000 - 317,000; Full time

Job summary

TikTok is seeking a Software Engineer to join the Model Infrastructure team in San Jose, focusing on infrastructure for large-scale model training and LLM serving. The role emphasizes distributed systems, GPU optimization, and collaboration with researchers to deploy high-performance AI solutions.

Applicants should have a CS degree and strong C++/Python skills, with knowledge of Transformers and PyTorch/TensorFlow. This is a full-time, on-site position with competitive compensation.

Qualifications

• Bachelor's degree in Computer Science or related field.
• Strong programming in C++ or Python.
• Solid understanding of data structures, algorithms, and systems.
• Familiarity with PyTorch or TensorFlow.
• Knowledge of Transformer architectures and LLMs.
• Strong problem-solving and passion for AI systems.
• Preferred: hands-on LLM training or inference experience; distributed training concepts; GPU programming.

Responsibilities

• Build and optimize infrastructure for large-scale model training and online inference.
• Develop distributed systems supporting large recommendation models and LLMs.
• Improve training and inference performance via GPU optimization and efficient communication.
• Collaborate with researchers to deploy LLM training and serving solutions.
• Analyze bottlenecks and implement performance improvements.

Skills

Bachelor's degree in Computer Science/

C++ or Python

Data structures & algorithms

Transformer & LLM basics

Problem solving for AI systems

Education

Bachelor's degree in Computer Science or related discipline

Tools

PyTorch

TensorFlow

CUDA

Triton

Job description

TikTok is seeking a Software Engineer to join the Model Infrastructure team in San Jose, focusing on infrastructure for large-scale model training and LLM serving. The role emphasizes distributed systems, GPU optimization, and collaboration with researchers to deploy high-performance AI solutions.

Applicants should have a CS degree and strong C++/Python skills, with knowledge of Transformers and PyTorch/TensorFlow. This is a full-time, on-site position with competitive compensation.