Taco
Taco is one of the fast golang-based message push systems in the company, and have serviced 300 million user. Taco provides multiple push methods such as pushing a single user, pushing a group of users in batches, and accurately pushing specific user tags. The low-latency feature greatly empowers the logistics rider’s message reach scenario.
Taco is an Infura-like, API gateway on top of Golang backend services, MySQL and Redis, RabbitMQ and Kafka as the messaging queue, Hive, Blink and Elasticsearch as data statistics and message pipeline query, gRPC, Apache Thrift and HTTP as the communication protocol, which gRPC and Apache Thrift is for internal communication protocol, HTTP is for iOS/Android/H5 external communication protocol.
I am a research-oriented machine learning systems engineer working on foundation model infrastructure, alignment, and evaluation. My work focuses on building efficient, reliable systems for large language models while studying the algorithms and data choices that make these models more useful, controllable, and cost-effective in real applications.
At TikTok, my recent work centers on Model-as-a-Service platforms and high-performance LLM inference. I develop serving infrastructure with vLLM and SGLang across model runtime integration, scheduling and continuous batching, KV-cache and memory management, distributed execution, observability, and reliability. This systems work is closely connected to my research on distributed disaggregated inference, preference optimization, instruction-tuning data selection, multimodal evaluation, and retrieval-augmented biomedical summarization.
My broader research spans reinforcement learning for robotics, healthcare sequence modeling, privacy-preserving machine learning, and motion planning. I am especially interested in model-system co-design: how model architecture, inference algorithms, data curation, hardware utilization, scheduling, and distributed runtimes interact. My goal is to advance frontier AI systems that are faster to experiment with, more rigorous to evaluate, and dependable enough to serve at scale.