Yuehan Lian

AI Compiler Framework: https://github.com/openvinotoolkit/npu_compiler Model Optimization - Apply quantization, pruning, and graph optimization techniques for efficient inference in the latest LLM and other AI models. - Analyze and optimize model performance using profiling tools and hardware metrics. Performance Benchmarking - Develop and maintain benchmarking suites for model and hardware performance comparison across platforms (NPU and CPU), especially in the Intel's latest NPU - Panther Lake. - Generate and analyze performance reports to guide optimization strategies. Deployment & Integration - Package and deploy AI models into end-to-end applications or SDKs. - Integrate AI inference pipelines into production systems, ensuring reliability and scalability. - Contribute to pipelines and reproducible experiment tracking.

Go / MySQL / gRPC / Kubernetes / Protobuf • Developed data interfaces and unit tests. Deployed service on cloud containers using tRPC, Kubernetes, and MySQL. • Containerized Tencent Cloud Content Delivery Network (CDN) configuration center environment with Docker. • Deployed Prometheus and Grafana to visualize performance, API call success rate, and database request error rate. • Manipulated more than * million records of CDN customers. Increase *% query speed by restructuring.

•Implemented backend for P4 target traffic filter running on Barefoot switch, interacting with Tofino ASIC chip. • Provided Restful APIs with Golang, gRPC, and MongoDB for monitoring and managing network ports. • Utilized Python package scapy to create IPv4/IPv6/VLAN packets, as well as sniff or filter packets to automate unit tests. • Investigated Barefoot Context interface failures due to concurrency with GDB when multiple ports are updated

Courses: Discrete Mathematics, Data Structure, Computer Algorithm Design and Practice, Software Engineering, C++ Program and Design, Java and Advanced Application, Web Design; Principles of Computer Composition, Computer System Architecture, Operating Systems, Compilation Principle, Computer Network; Digital Image Processing, Computer Graphics (Bilingual); R Data Processing, Data Mining.