• Research, develop and publish on different projects taken up by the Software Directorate at NCSA.• Developed a customizable and scalable open-source data management platform (clowderframework.org) hosting GPT models for sentence and document classification in a Kubernetes cluster. Developing intelligent document parsing based on LLMs to automatically assess quality of medical publications and give feedback to authors and reviewers as to whether the paper meets the review criteria.• Implementing agents in LangChain for writing and executing RNA Sequencing analysis pipeline. Uses Github webhooks for human interaction, Plan and Execute agent workflow with OpenAI and Azure GPT4 models, LangGraph for async agent action control, and Ray to run distributed Python workloads.• Developing a platform for distributed ML training and inference on HPC clusters hosted by NCSA.• Developing RAG agents to analyze email dataset and explore the reasoning behind changes to the business model for SHEILD Illinois Initiative to make the innovative saliva-based COVID testing available to the public.• Developing a platform for distributed ML training and inference on high performance computing clusters hosted at NCSA.• Backend platform design and development on Rokwire (rokwire.org) - an interdisciplinary project at University of Illinois for building an ecosystem for smart, healthy, and connected communities.• React-Redux web application for an open-source data management platform for National Institutes of Health Randomized Clinical Trial publications. Topic classification using BERT and GPT based models.• Automation of data processing pipeline to support submission of open-source weather data (Ameriflux ameriflux.lbl.gov) from crop sites.• Member of ML Special Interest Group - created study materials for RSE's to learn ML. - led Round Table discussions & Hands-on sessions on ML & RAG.• Conferences attended : - NeurIPS 2022 - AGU 2022 - US-RSE 2023 - US-RSE 2024

• Developing an Applicant Tracking System(ATS) that leverages NLP for unbiased and efficient bidirectional job matching, as 62% of the recruiters feel that qualified candidates are overlooked by current ATS solutions.• Designing a scalable ensemble data pipeline using BERT and XGBoost for capturing context from resumes.• Managed a team of 3 engineers, practicing agile workflow and wrote the product road map for the ATS.

Lecturer for CS 480 - Introduction to Artificial Intelligence for Spring 2022Developed, organized, and taught IITs official introductory course on Artificial Intelligence methods and applications.

• Developed a credit lending web application served with Streamlit app with the view of expanding financial access and control to underserved communities. (github.com/minump/Insight-Project)• Explored holistic mobile app data and financial data to predict the risk of defaulting.• Investigated potential biases using XGBoost model, SMOTE technique and SHAP values.• Deployed a production-level containerized application using GKE that enables scalability and load balancing.• Thrived in a fast-paced and self-driven environment, which required the completion of weeklydeliverables, highly time-sensitive tasks, and regular progress update presentations to technical and non-technical stakeholders

Conducted resume peer reviews, participated in various tech and social activities.

• Developed an in-house machine translation model using Transformer model with domain classification to enable domain specific documents to be translated from foreign language to English.• Used Tensorflow for multi-gpu training in GCP and Spacy for tokenization.• Achieved an improvement of 17% from the baseline model with BLEU score of 41 on client documents.• Presented to the CEO of Genpact

• Implemented a data warehouse management application for a top energy company in the UK, using the technology stack of SQL, PLSQL and Bash scripts.• Translated business requirements for adhoc data requests into customized SQL queries.• Improved the ETL throughput by creating an index for the application.• Documented the entire process to help the team in understanding all technical aspects of the application.

• Delivered tech support for various cellular clients by handling server administration covering the areas of 2G & 3G performance management, configuration management & fault management.• Performed system testing, data recovery, data cleansing and validation using shell scripts and SQL queries to maintain the system during regular and outage situations.• Resolved emergency situations by coordinating and escalating with relevant teams.