Software Engineer - Model Infrastructure, TikTok Feeds

What you'll do

• Develop scalable infrastructure for recommendation-model inference and training, addressing compute, storage, and deployment bottlenecks.
• Collaborate with algorithm researchers to co-design infrastructure for machine-learning frameworks and hardware accelerators.
• Improve model architecture, efficiency, and scalability, and build reusable components and tools.

What they ask for

• Bachelor’s degree or above in Computer Science or a related field.
• Understanding of GPU architecture and its software stack, with experience in GPU performance analysis.
• Experience with at least one machine-learning framework.
• Ability to work independently and collaboratively in a fast-paced team environment.

Nice to have

• Familiarity with deep-learning network implementation details and low-level operators; experience with large-scale distributed model training.
• Knowledge of DNN compilers such as MLIR, XLA, or TVM; ability to analyze and optimize training or inference algorithms using mathematical tools.

Tools

CUDA, CUTLASS, Triton Lang, TensorFlow, PyTorch, MLIR, XLA, TVM

AI focus

Build infrastructure for recommendation-model inference and training, including systems that support large foundation models in computer vision, NLP, and multimodal applications.