About - Full Story

I like pasta and art, and follow a versatile daily workout routine 😎. My friends and family know me by my contagious smile. I think I am friendly and entertaining to sit next to. I am interested in a number of subjects as I like to be jack of all trades. I am fascinated by topics related to computer science, psychology, astrophysics, and in general, anything scientific. I have been lately following the science of climate change and am deeply interested in helping the fight of climate crisis. Well, more urgently, I am now very interested and working in safe AI (making sure AI does not do harm or take over humanity). 

More work-related, I am an AI Researcher in and affiliated with Yonsei University and SNU. I am working on Safety and ethics in LLMs.

Previously I was an AI Research Scientist at Meta AI (Facebook AI) and worked briefly on deepfake detection, and developed technologies for privacy-preserving machine learning and federated learning. I contributed to Opacus, an open-source library that enables training deep learning models with differential privacy, and FLSim, an open-source library for simulating federated learning systems.  I publish papers too.

I was a Visiting Researcher at University of California, Berkeley and member of the Berkeley Artificial Intelligence Research (BAIR). When I was at UC Berkeley, I contributed to FLOW, an open-source  deep reinforcement learning-enabled framework for simulation of autonomous and manned cars. 

I earned my graduate degree in Computer Science at the University of Texas at Dallas. My work was on the intersection of Computer Systems, Edge Computing, and Machine Learning, specifically, on improving quality of service in IoT and deep learning Applications through Fog Computing. I won the UT Dallas Best Dissertation Award. While at UT Dallas, I created Fog Computing Conference Hub.

I was TA and unoffical lecturer at UT Dallas, and two-time recipient of Best Teaching Assistant Award. I like to contribute the open-source community, and so I served as technical program committee for FL-ICML, FL-NeurIPS, AIChallengeIoT, and reviewer of several international journals and conferences, including ICML, NeurIPS, IEEE/ACM TON, IEEE TNSM, TMC, NETWORK, TSC, IoTJ, INFOCOM, and ICDCS.

Prior to all these, I was a web-design freelancer for few years: I found my interest in graphic design in early high school and initially pursued it as a hobby. I designed logos, posters, and business cards for individuals and small companies. Later on, I learned web development and started designing websites, as a solo developer and designer (it was back-end and front-end coding, and graphic design). I gathered a team of designers and founded irDraw (no longer operating), where we were involved in web development and graphic design. I designed and developed 15 websites for different businesses before changing my focus to PhD.