Summary
Jiawen Wang is an Advanced AI Engineer with a decade of experience building and scaling LLM serving and inference infrastructures across industry and research settings. He has designed and productionized hybrid-cloud, Kubernetes-based multi-model serving systems—supporting high-throughput services (300K DAU, 800 RPM) and OpenAI-compatible APIs—while working on domain-specific LLM training and deployment. Proficient in Java, Python, Go and modern ML stacks (PyTorch, vLLM, Hugging Face), he bridges backend engineering (SpringBoot, Docker, Nginx, MySQL/Redis) with ML infra and model-serving features like streaming, tool calling and rate limiting. His background spans fintech, vision research and medical data mining, and he maintains active personal projects on GitLab dating back to his early engineering years. Based in Hong Kong, he combines rigorous academic training from NUS with hands-on production experience at Lenovo and CATL, making him adept at taking research models into reliable, enterprise-grade services.
10 years of coding experience
2 years of employment as a software developer
Bachelor of Engineering - BE Communication Engineering, Bachelor of Engineering - BE Communication Engineering at Jilin University
Master of Science - MS Electrical and Computer Engineering, Master of Science - MS Electrical and Computer Engineering at National University of Singapore