Responsible for the search system of TikTok and its affiliated products, and solving the architecture optimization problem of the search architecture system;
Focus on architecture abstraction and process optimization for search scenarios, support large-scale machine learning optimization;
Focus on large-scale systems with high concurrency and high throughput, improve system stability, performance, and scalability;
...
Design and optimize recommendation system architectures to improve development efficiency, performance, scalability, and recommendation effectiveness across feeds and vertical content scenarios.
Build and optimize backend systems and services for data security, modularity, computational efficiency, and scalability.
Ensure production system stability through troubleshooting, mechanism design, and tooling development.
...
Design and evolve scalable recommendation system architectures supporting multi-scenario business requirements across feeds and vertical content
Build high-performance distributed storage systems and computing frameworks optimized for recommendation workloads
Trouble-shooting of the production system, design and implement the necessary mechanisms and tools to ensure the stability of the overall operation of the production system
...
Design, build and optimize distributed training infrastructure and low-latency online inference systems for large-scale recommendation models and Large Language Models
Develop high-performance GPU kernel implementations and efficient inter-node communication primitives to improve training and inference efficiency
Build compiler optimization passes and operator fusion technologies for deep learning frameworks to accelerate model execution
...