Work Experience
IBM Research
AI Research Intern
May 2023 - Present
Hosted by the Generative Model Alignment team, developing a novel approach for improving the self-refinement / self-correction capabilities of Large Language Models (LLMs) via in-context learning. Exploring the application of this method for conversational AI through knowledge distillation and self-training.
IBM Research
AI Research Intern
May 2022 - August 2022
Hosted by the Multilingual NLP Group, focusing on semantic parsing, as one of the few undergraduate interns in the IBM Research's AI division. Working on Text-to-RDF Graph parsing, exploring graph structure representations and fine-tuning pre-trained sequence-to-sequence Large Language Models (LLM).
Perelman School of Medicine - University of Pennsylvania
Machine Learning Research Assistant - URBS Lab
Jan 2021 - Dec 2021
Supervised by Prof. Ryan Urbanowicz, worked on an AutoML system with deep learning methods (AutoMLPipe-DL), to compare its performance to AutoML systems with classical Machine Learning algorithms for classification tasks with electronic health record (EHR) data.
​
Used probabilistic graphical models (deep learners) as unsupervised feature extractors for high-dimensional noisy tabular data, serving as a denoising technique, and demonstrated its efficacy on classification tasks in the AutoML setting.
Wharton Analytics Fellows (WAF)
Senior Data Analyst
Jan 2021 - Dec 2021
In Fall 2021, worked with The Zillow Group on large-scale customer segmentation using an approach considering customer states across time periods. We used clustering approaches to define customer segments, and assigned labels to represent their current states, enabling supervised learning in a multi-label multi-class classification setting.
Read the feature article on my team's work here!
In Spring 2021, worked with Fox Entertainment Corp. on outlier detection and viewership prediction with social media marketing data for show premieres and campaign lead-up. Used clustering methods and trend analysis to identify particularly successful campaigns, and presented our analysis to company executives, which was well received.
Cary Institute for Ecosystem Studies
Data Science Intern
Jul 2018 - Dec 2018
Worked with Dr. Barbara Han and Dr. Ilya Fischhoff in the Han Lab, explored machine learning and data science-based approaches for epidemiological applications. Used data mining techniques with Python and R to examine the top keywords in specific Google Trends categories affiliated with zoonotic diseases at different spatial scales, as potential early warning indicators.