Hi, I'm Reetu

I build machine learning systems and ship them to production: pipelines, models, APIs, and the evaluation harnesses that keep them honest.

Over 7 years across manufacturing, supply chain, retail pricing, and ecommerce, I've built demand forecasting for 6,500+ SKUs across five plants and deployed a pricing model behind a REST API that cut turnaround from 30 minutes to 5 seconds, both with automated retraining and monitoring.

Lately I've been working with LLMs: agentic RAG with LangGraph and Llama 3.1, multi agent workflows with CrewAI, and evaluation harnesses using RAGAS.

Toolkit: Python, SQL, PyTorch, Spark, Kafka, Databricks, Snowflake, dbt, MLflow, AWS, Azure

M.S. Computer Science, RIT. Research on ML surrogates for thermal prediction published at ASME FEDSM 2026.

Vehicle Price Prediction with AWS CI/CD  

Used car data → CatBoost / XGBoost model bake-off → Flask app → Docker → Amazon ECR

A web app that predicts the fair price of a used car from details like brand, year, mileage and accident history. Several models are trained and compared to pick the best performer, and every code push automatically builds a Docker image and deploys the app to AWS through GitHub Actions.

→ All Data Science & ML projects

AI Powered Financial Document Analysis  

Financial PDFs → FAISS + BM25 hybrid retrieval → LangGraph agent → Llama 3.1

An AI system that reads financial reports and answers questions about the numbers inside them, reviewing and correcting its own answers before responding. It scored 41.5% on FinanceBench — more than double the 19% scored by GPT 4 Turbo.

→ All AI & GenAI projects

ML & Modeling

GenAI & LLMs

Cloud & DevOps

• ASME FEDSM 2026 — Machine learning for instant prediction of spatial temperature variations in heat sinks for computer chip cooling
• Published — Towards utilizing machine learning and computational fluid dynamics in the classroom for high heat dissipation
• ✍️ Blog posts on Medium