Curriculum Vitae (CV)

🔗 Downloads: [ Resume (EN) ] [ Resume (한국어) ]

🎓 Education

• M.S. in Artificial Intelligence
  🏫 Korea Advanced Institute of Science and Technology (KAIST) — Seoul, South Korea (Expected 2026)
  • Graduate Student Researcher at MLAI Lab
  • Advisor: Prof. Sung Ju Hwang
• B.S. in Computer Science (Minor: Data Science)
  🏫 Lehman College, City University of New York — New York, NY (2022)
  • 🏅 summa cum laude
  • Overall GPA: 3.97/4.00

💼 Work Experience

Graduate Student Researcher

MLAI Lab, KAIST — Seoul, South Korea (March 2024 – Present)

• Conducting research on large language models (LLMs) with a focus on:
  • Improving elite sample selection for in-context learning.
  • Enhancing few-shot image classification tasks.

Data Scientist

Penta Group — New York, NY (September 2021 – February 2024)

• Designed and implemented a social listening tool for TikTok using AI-driven transcription and topic modeling.
• Deployed Python analytical tools as web-based solutions for analysts.
• Developed innovative data mining techniques for media streams (traditional and social).

Data Science Fellow

Wall Street Journal — New York, NY (August – December 2021)

• Built machine learning models to predict article performance based on headlines.
• Optimized SQL queries and streamlined real-time data processing pipelines.

Mixed-Reality Research Intern

NASA Langley Research Center — Hampton, VA (August 2019 – August 2021)

• Created VR applications for data visualization using Unity3D and Unreal Engine.
• Designed heat-map visualization tools and explored VR-specific UI/UX concepts.
• Conducted stakeholder interviews to inform user-centric development processes.

🔍 Research Experience

Graduate Student Researcher

MLAI Lab, KAIST — Seoul, South Korea (2024 – Present)

• Exploring advanced techniques in in-context learning and large language models (LLMs).

Researcher, Data Science

York College, City University of New York (2022)

• Developed automated methods for scraping and extracting indigent burial data.
• Conducted analysis for the Population Association of America Conference.

Project Owner

Public Interest Technology Data Science Corps, Columbia University (2022)

• Managed and mentored a team of five undergraduate researchers.
• Directed projects addressing equity and public interest technology challenges.

Data Science Research Fellow

Lehman College, City University of New York (2021)

• Automated data extraction from PDFs using OCR with over 90% accuracy.
• Built datasets representing public health profiles for analytical purposes.

🛠️ Skills

• 💻 Programming Languages: Python, R, SQL, C#, C++, Git
• 📚 Frameworks: TensorFlow, PyTorch, Scikit-Learn, NLTK, Keras
• 🛠️ Software: Jupyter Notebooks, Pandas, Excel
• 🔍 Research Focus: Large Language Models (LLMs), In-Context Learning, Few-Shot Learning, NLP
• 🌐 Languages: English (Native), German (Proficient), Korean (Elementary)

📚 Publications

EnDEVR: An Environment for Data Engineering in VR

Lehman, Sarah M., Campbell, Newton H., Aytes, Simon A., Kirshner, Mitchell, & Arviola, Anthony. (2021). "EnDEVR: An Environment for Data Engineering in VR." IEEE.