Open to roles in Artificial Intelligence and Machine Learning

Hi, I'm Pranav Dhawan

Currently building agentic automation at American Chemical Society, Washington DC. MS in Data Science from George Washington University.

View My Work Get In Touch
Pranav Dhawan

ABOUT ME

I’m an AI Engineer and Data Scientist working on production systems and model pipelines. I hold a Master’s in Data Science from George Washington University and a Bachelor’s in Computer Science and Engineering. My experience spans computer vision, natural language processing (NLP), and analytics, with a focus on transforming messy data into reliable, scalable solutions.

I’ve recently been working on AI agents, context compression, and workflow automation. I’m drawn to problems that involve navigating ambiguity, optimizing under constraints, and building systems people actually use.

Always open to connecting with others working on interesting problems so feel free to reach out.

Experience with
  • American Chemical Society
  • EY
  • HCLTech
  • Lumina Datamatics

SKILLS & TECHNOLOGIES

Language ML Data & Cloud Visualization AI
Skills graph Static graph showing relationships between my skills: programming languages (Python, R); ML and data libraries (Pandas, NumPy, scikit-learn, Matplotlib, Seaborn, PyTorch, TensorFlow, HuggingFace); databases and cloud platforms (SQL, AWS, GCP); visualization tools (Power BI, Tableau, Streamlit); and AI agent frameworks (n8n, Agentic AI, LangChain, CrewAI). Nodes can be hovered, tapped, or focused with the keyboard to highlight connections.

FEATURED PROJECTS

Stock Screen

Stock Screen

A real-time AI-powered terminal that unifies stock analysis, market news, company filings, forecasting workflows, and market context into a single interface. Designed for investors, it helps compare signals quickly and turn live market data into actionable research.

GCP Python ML
Live demo
Multimodal Techniques for Equity Forecasting

Multimodal Techniques for Equity Forecasting

Conducted a benchmark study on the FinMultiTime dataset using multiple data modalities, evaluating 10+ different model architectures and ensembles delivered findings in a research paper and technical report.

Python LSTM FinBERT Attention
Code
Edge-Based PII Detection & Censoring System

Edge-Based PII Detection & Censoring System

Achieved 98.1% F1-score and 97.9% recall across 54 PII entity types by architecting and benchmarking 4 transformer architectures, selecting DeBERTa as the production model and deploying via ONNX for <100ms inference.

DeBERTa ONNX Streamlit
Code
Serverless ETL — Weather Dashboard

Serverless ETL — Weather Dashboard

Built a fully serverless ETL pipeline on AWS using Lambda and EventBridge to ingest and transform real-time weather data from the OpenWeather API on a scheduled cadence, with results surfaced through an interactive dashboard.

AWS Lambda EventBridge OpenWeather API
Code

PROFESSIONAL EXPERIENCE

June 2026 - Present
Current

AI Independent Contractor

Siva Info LLC | New York, NY | Part-time, Remote

Building AI-driven document processing workflows for journals, academic papers, and books using rule-based scripting, local LLMs, and document comparison pipelines.
Developed change-manifest tooling to compare two versions of source files, identify content and formatting changes, and guide updates across downstream deliverables such as presentations, reports, and publication materials.
Reduced manual document review effort by automating repetitive change-detection and deliverable-update workflows for high-volume academic and publishing content.
Technologies Used:
Local LLMs Document Processing Rule-Based Scripting Pipeline Automation
May 2026 - Present
Current

AI Workplace Engineer Intern

American Chemical Society | Washington, DC | Full-time, Hybrid

Automated ~70% of monthly Ivanti Neurons service desk tickets by connecting email intake to a RAG-enabled workflow that classifies requests, drafts responses for information tickets, and routes complex issues to staff with suggested solutions and relevant SharePoint/Wiki sources.
Designed and implemented a Copilot Studio pilot program to evaluate enterprise AI use cases, build internal workflow prototypes, and support adoption of M365 Copilot for service desk and workplace automation.
Established an AI governance blueprint covering data protection, secure knowledge-base access, human-in-the-loop review, token misuse prevention, and responsible deployment standards for internal AI workflows.
Technologies Used:
RAG Ivanti Neurons Copilot Studio M365 Copilot AI Governance Human-in-the-Loop Automation
August 2024 - May 2026
Graduated

Master of Science, Data Science

George Washington University | Washington, DC

GPA: 3.74/4.0

Published a journal paper from the Multimodal Techniques for Financial Time Series Forecasting capstone project.
Completed dataset reports analyzing U.S. government health, CBP.gov, and WMATA datasets.
Relevant Coursework:
Machine Learning Deep Learning NLP Data Mining Cloud Computing Time Series Analysis
February 2024 - August 2024

Machine Learning Engineer

Lumina Datamatics | Chennai, India | Full-time

Developed and fine-tuned computer vision pipelines to detect and extract complex equations from 10,000+ unstructured documents, improving technical content digitization and reducing manual review effort.
Refactored the document layout parsing architecture by replacing legacy LayoutParser components with a custom pipeline, improving extraction accuracy by 16% and reducing inference latency by 0.3 seconds per page.
Architected a Retrieval-Augmented Generation system for legal document search across 10,000+ documents using fine-tuned BART/BERT-based models, optimized embeddings, and FAISS indexing, reducing query retrieval time from minutes to under 5 seconds.
Operationalized machine learning workloads on AWS SageMaker, enabling scalable processing for high-volume document intelligence pipelines.
Technologies Used:
Python YOLO Computer Vision RAG BART/BERT FAISS AWS SageMaker
August 2020 - July 2024
Graduated

B.Tech in Computer Science and Engineering

Manipal University Jaipur | Rajasthan, India

GPA: 8.51/10.0

Wrote a comparative analysis paper on transformer models versus LSTM for sentiment classification across the X platform.
Relevant Coursework:
Algorithms & Data Structures Database Management Systems
July 2023 - September 2023

Machine Learning Intern

HCLTech | Noida, India | Internship, Hybrid

Built predictive workforce analytics models using Logistic Regression and Random Forest to successfully identify key productivity drivers across 500+ employees.
Engineered 12+ data-driven KPIs from raw employee activity logs, including screen time, application usage, and behavioral activity patterns, using SQL and Python.
Applied clustering and statistical analysis to identify high-performance employee segments and surface productivity anomalies for cross-team benchmarking.
Designed interactive Tableau dashboards to visualize productivity trends, enabling management teams to make data-backed workforce planning decisions.
Technologies Used:
Python SQL Logistic Regression Random Forest Tableau
May 2023 - July 2023

Summer Intern

EY | Gurugram, India | Internship, Hybrid

Developed Power BI dashboards for Sales and HR functions, visualizing revenue trends, customer acquisition, headcount, attrition, and compensation benchmarks.
Automated ETL workflows using Alteryx to extract, clean, and transform data from 5+ sources, improving reporting consistency and eliminating manual data handling errors.
Supported monthly business review reporting with validated, accuracy-focused data preparation workflows.
Technologies Used:
Power BI Alteryx ETL Data Visualization

GET IN TOUCH

Download Resume

dhawanpranav02@gmail.com

Or send me a message directly