Pfizer logoPfizer Externship via Extern·🟢 Open to work

Computer Science freshman at Purdue building practical coding foundations

I am a Purdue first-year studying Computer Science, learning core programming, algorithms, and software fundamentals while preparing for hands-on projects and internships.

View my workMessage Me

Work samples

I am compiling coursework and small projects that show my programming practice, problem solving, and growing familiarity with CS tools and concepts.

  • Vehicle Crash Risk Prediction
    Vehicle Crash Risk Prediction

    Built a machine learning pipeline using NHTSA’s FARS 2024 national crash dataset to predict crash injury severity and generate continuous 0–100 insurance risk scores Trained a RandomForestClassifier with class-weight balancing to address class imbalance, using predict proba() outputs to drive a premium-multiplier scoring function Structured the project into modular components (preprocessing, training, prediction) and resolved dtype/environment issues in a Jupyter/VS Code workflow

    Pythonscikit-learnJupyterVS Code
  • Real-Time Color-Detection Aim Assistant
    Real-Time Color-Detection Aim Assistant

    Built a real-time computer-vision tool that continuously scans the screen for target colors and automates cursor movement and clicks, built to compensate for imprecise aim without a physical mouse Iterated past single-color detection after discovering it broke on varying in-game character skins, adding detection logic to disambiguate targets using more than color alone Diagnosed latency in the real-time screen-capture loop as the main performance bottleneck under continuous operation

    Python

About me

I am a Purdue first-year studying Computer Science, learning core programming, algorithms, and software fundamentals while preparing for hands-on projects and internships.

I am Rohan D, a first-year Computer Science student at Purdue University pursuing a bachelor's degree. I am at the start of my career journey, building foundational skills in programming and computer science while exploring areas to focus on next.

Externships

Pfizer Advanced: AI-Powered Document Insights & Data Extraction Externship

In progress

Experience

NASA Engineering Scholars Program Intern

NASA Glenn Research Center · August 2025 – June 2026

Software Engineer Intern

Cleveland Clinic Akron General · June 2025 – August 2025

Education

Purdue University

B.S. in Computer Science · Class of 2029

Skills

Programming fundamentalsAlgorithms and data structuresProblem solvingIntroductory software developmentLearning new languages and tools
Back to work

Vehicle Crash Risk Prediction

Built a machine learning pipeline using NHTSA’s FARS 2024 national crash dataset to predict crash injury severity and generate continuous 0–100 insurance risk scores Trained a RandomForestClassifier with class-weight balancing to address class imbalance, using predict proba() outputs to drive a premium-multiplier scoring function Structured the project into modular components (preprocessing, training, prediction) and resolved dtype/environment issues in a Jupyter/VS Code workflow

Pythonscikit-learnJupyterVS Code
View all work
Back to work

Real-Time Color-Detection Aim Assistant

Built a real-time computer-vision tool that continuously scans the screen for target colors and automates cursor movement and clicks, built to compensate for imprecise aim without a physical mouse Iterated past single-color detection after discovering it broke on varying in-game character skins, adding detection logic to disambiguate targets using more than color alone Diagnosed latency in the real-time screen-capture loop as the main performance bottleneck under continuous operation

Python
View all work
Back to work
Pfizer ↗

✅ Verified by Extern · ⏱️ In progress

Pfizer Advanced: AI-Powered Document Insights & Data Extraction Externship

Prototype AI-powered document intelligence with Pfizer—using OCR, LLMs, and RAG to automate real enterprise PDF workflows and build a standout portfolio project.

AI & MLPythonDocument IntelligencePresentation Skills

Overview

The externship developed a prototype pipeline that combined OCR, LLMs, and retrieval-augmented generation to extract and summarize information from enterprise PDFs. The work surveyed LLM architectures and integration patterns, evaluated OCR-to-RAG workflows, and produced a documented prototype for automated document processing.

Pfizer Advanced: AI-Powered Document Insights & Data Extraction Externship

What I've accomplished

I produced explanatory documentation that detailed LLM tokenization, Transformer attention mechanics, and the training progression from unsupervised pretraining to supervised fine-tuning as applied to pharmaceutical documents.

Project breakdown

I explained how LLMs tokenized input, used Transformer attention to compare tokens in parallel, and generated text one token at a time. I also summarized training steps, from large-scale unsupervised pretraining to supervised fine-tuning.

During the externship I cleaned structured data with Pandas, parsed nested JSON into tabular form, standardized inconsistent text via replacement dictionaries, and applied image preprocessing (grayscale, denoising, blurs, histogram equalization) to improve OCR readiness.

Open Link
View all work