Latest Content

How to deploy and serve multi-host gen AI large open models over GKE
Nov 26, 2024
Article

As a Software Engineer Manager at Google, I lead a team of engineers to enable customers train and run GenAI OpenModels over K8s/GKE. With over 15 years of experience in software development and distributed systems, I have a proven track record of delivering large-scale, high-performance, and reliable solutions for enterprise products and cloud infrastructure.

My core competencies include Kubernetes, Docker, container technologies, and edge computing, which I have applied and advanced in various roles and projects. For example, I contributed to the launch of Azure OpenAI service with GPT3 model as a Principal Software Engineering Manager at Microsoft, and I co-chaired the Kubernetes IoT/Edge workgroup and led the CNCF sandbox project, Kubeedge, as a Senior Cloud Software Architect at Huawei. With two years' tenure at Meta, I gained experiences building & managing a new team with fast growth pace and lots of ambiguities. I am passionate about new challenges and opportunities where I can use my skills and expertise to create value and impact.

1
article