Summary
Yifan Liu is a pragmatic software engineer and recent Michigan grad now pursuing an MS in Computer Science at UC San Diego, with three years of hands-on experience building full-stack systems and production AI services. He has delivered scalable features at TikTok, including an IDE plugin used by 5,000+ developers that cut unit-test authoring time by 85%, and engineered efficient PSI-based context extraction and streaming model integrations to achieve low-latency, secure inference. At startups he built customer-service and image-generation platforms processing millions of logs and 100k+ records, fine-tuned large LLMs (Qwen series) with LoRA to cut loss and inference time substantially, and deployed RAG/agent pipelines with sub-0.2s response times. Comfortable across C/C++, Python, OCaml, and JavaScript, he pairs systems-level performance tuning (runtime caps, token pruning, payload compression) with practical ML engineering and async production deployments. Notably, he combines deep implementation skill with a penchant for measurable impact — speeding workflows and trimming resource use rather than just prototyping features.
3 years of coding experience
1 year of employment as a software developer
University of California, San Diego
Bachelor's degree, Computer Science, 3.988/4.000, Bachelor's degree, Computer Science, 3.988/4.000 at University of Michigan
Bachelor's degree, Electrical and Computer Engineering, 3.7, Bachelor's degree, Electrical and Computer Engineering, 3.7 at 上海交通大学