Working under Dr. Carson Tao at the Computational Research Team at Sumitomo-Pharma America (contracted)• Architected and implemented an end-to-end automatic speech-to-text system (from data pipelines to model re-training) that transcribes and de-hallucinates doctor-patient conversations for the extraction of meaningful audio and linguistic signals.• Prompt-engineered and deployed LLMs such as GPT-4, GPT-3.5, Mistral-7B, Llama-3 for speaker diarization with zero-shot, few-shot and chain-of-thought learning approaches.• Fine-tuned Mistral-7B-Instruct and Llama-3 models using PEFT-based approaches, including LoRA, QLoRA, DoRA, and QDoRA, for speaker diarization pipeline, achieving state-of-the-art results.• Conducted evaluation of internal SMPA pipeline against open-source and proprietary ASR models from Google Cloud, Amazon, and Microsoft Azure and achieved SOTA results for multi-lingual recordings.

• Orchestrated distributed ETL pipelines for a production Redshift data warehouse that streamlines sales team tracking and analysis for improved customer targeting.* Led the design and implementation of an automated AWS Lambda-based ETL pipeline, extracting and integrating data incrementally from RAVE Medidata API into AWS Aurora.* Created 20+ data jobs with SCD2 and history tables using SQL and Matillion for Redshift.* Collaborating with data engineers and Urovant consultants to normalize pharmaceutical data.

* Fine-tuned BioBERT, ClinicalBERT, ClinicalLongformer language representation models for automated patient chart review for identification of care preference documentation.• Sped up data wrangling and analysis by 50x by building custom software packages using PySpark for ETL between PostgreSQL servers and ML models.• Developed data extraction pipeline for transforming raw EHR data for contained in MIMIC-IV database into dataframes for easy integration into existing ML pipelines using dask, pandas, numpy libraries* Received $5000 USD in research funding, awarded High Honors in Computer Science, submission accepted at IEEE ICSC/AIMHC '24

Teaching Assistant for CS 1, CS30* I grade assignments, midterm and final papers for the Introductory Computer Science course at Dartmouth* I lead weekly review session for 10 students to review key CS concepts such as coding etiquette, data structures, objects & classes, recursion.* I hold 5+ hours of office hours every week to assist students with understanding and applying concepts, working on lab assignments and preparing for exams.

Tutoring Dartmouth Students in the following classes: Introduction to Computer Science (COSC 1), Object Oriented Programming (COSC 10), Introduction to Calculus (MATH 3)

Under the supervision of Professor V.S. Subrahmanian at The Institute for Security, Technology, and Society (ISTS). Working on Android malware detection, machine learning, and smartphone application security.

Working under Dr. Dhananjay V. Gadre, ECE Department. Working with embedded systems and their applications, such as Arduino and MSP430.