2025 -
I co-founded Semalytica, a data platform focused on semiconductors,
turning complex manufacturing and test data into actionable insights.
Semalytica build advanced tools for fabs and engineering teams with deep insights from process, test,
and equipment data turning raw complexity into smart decisions that improve yield,
efficiency, and innovation.
We bring AI into semiconductor workflows, combining domain expertise, data infrastructure,
and customizable insight engines to unlock next-level manufacturing intelligence.
2024 -
I worked as software engineer in
2017 - 2022
During my internship at Advantech, I participated the development and deployment of AgentBuilder, an internal
GenAI
application development platform. In Q2 2024, we successfully integrated AgentBuilder with the company’s data
platform, DataInsight, and supported the factory team in building 12 generative AI applications within three
months. These solutions collectively saved dozens of work hours per week and were later rolled out
company wide in Q3 2024.
Beside, I deployed open-source LLMs using vLLM and SGLang inference engines and built an automated
benchmarking and performance evaluation pipeline. This system enables internal teams to test and compare LLM
performance across Advantech hardware products and has been internally open-sourced for cross-departmental
use, particularly by the hardware division.
2024
My PhD was focused on convolutional/recurrent neural networks and their applications in computer vision, natural
language processing and their intersection. My adviser was
Fei-Fei Li
at the Stanford Vision Lab and I also had the pleasure to work with
Daphne Koller,
Andrew Ng,
Sebastian Thrun and
Vladlen Koltun
along the way during the first year rotation program.
I designed and was the primary instructor for the first deep learning class Stanford -
CS 231n: Convolutional Neural Networks for Visual Recognition. The
class became one of the largest at Stanford and has grown from 150 enrolled in 2015 to 330 students in 2016, and
750 students in 2017.
Along the way I squeezed in 3 internships at (a baby) Google Brain in 2011 working on learning-scale
unsupervised learning from videos, then again in Google Research in 2013 working on large-scale supervised
learning on YouTube videos, and finally at DeepMind in 2015 working on the deep reinforcement learning team.
2022 - 2024
I participated in the Undergraduate Research Opportunities Program (UROP) hosted by the MIT Media Lab wehn study
in National Taipei University of Technology. As part of the City Science Group, I collaborated on projects that
leveraged advanced computational techniques
and urban data driven analytics to generate real world insight.
