About me

Machine Learning Scientist with 4 years of experience developing scalable models for the banking sector, alongside 5 years of research and 3 years in software engineering. Technical expertise spans machine learning and system integration. Strong communicator and a leader, with a focus on delivering solutions that align with business goals and driving impactful projects through cross-functional teamwork.

Interests

Deep Learning
Generative AI
Software Engineering
Teaching

Education

Ph.D. in Computer Science

University of North Carolina at Charlotte
M.S in Computer Science

University of North Carolina at Charlotte
M.S in Statistics (Tentative)

North Carolina State University

Work Experience

Vice President, Data Science

Bank of America

Apr 2025 – Present

Quantitative Analytics Specialist

Wells Fargo

Jul 2022 – Mar 2025

Developed machine learning models for fraud detection.

Model Interpretibility, Risk & Governance, XGBoost, PySpark, Hadoop

Quantitative Analytics Intern (NLP)

Wells Fargo

Jun 2021 – Aug 2021

Developed a new method for compressing the size of large natural language models based on the transformer architecture. Link to the paper.

Natural Language Processing, Transfomers, Model Compression.

Machine Learning Intern

Siemens

May 2019 – Aug 2019

Developed a new method for generating graph embeddings for faster link prediction in graphs. Link to the paper.

Link Analysis, Machine Learning for Graphs, PyTorch

Software Engineer

Aptean

Jun 2014 – Dec 2016

Software Development

C#, C++, SQL, Git

Recent Publications

Privacy Enhancement for Cloud-Based Few-Shot Learning

Accepted in IEEE WCCI International Joint Conference on Neural Networks (IJCNN), July 2022, Padua, Italy

Archit Parnami, Muhammad Usama, Liyue Fan, Minwoo Lee

PDF Code

Privacy Enhancement for Cloud-Based Few-Shot Learning

Learning from Few Examples: A Summary of Approaches to Few-Shot Learning

Few-Shot Learning refers to the problem of learning the underlying pattern in the data just from a few training samples. Requiring a …

Archit Parnami, Minwoo Lee

PDF

Learning from Few Examples: A Summary of Approaches to Few-Shot Learning

Pruning Attention Heads of Transformer Models Using A* Search

Recent years have seen a growing adoption of Transformer models such as BERT in Natural Language Processing and even in Computer …

Archit Parnami, Rahul Singh, Tarun Joshi

PDF

Pruning Attention Heads of Transformer Models Using A* Search

Transformation of Node to Knowledge Graph Embeddings for Faster Link Prediction in Social Networks

Accepted in ESWC 3rd International Workshop on Knowledge Graph Construction (KGCW), May 2022, Crete, Greece

Archit Parnami, Mayuri Deshpande, Minwoo Lee

PDF Code

Transformation of Node to Knowledge Graph Embeddings for Faster Link Prediction in Social Networks

Few-Shot Keyword Spotting With Prototypical Networks

Published in ACM 7th International Conference on Machine Learning Technologies (ICMLT), March 2022, Rome, Italy

Archit Parnami, Minwoo Lee

PDF Code

Few-Shot Keyword Spotting With Prototypical Networks

Skills