Yadu Sarathchandran, PhD

Yadu Sarathchandran, PhD

Data Scientist  ·  Machine Learning Engineer  ·  Physicist

View Projects Get in Touch
Scroll
Introduction

About Me

Experienced researcher specializing in machine learning, statistical analysis, and data engineering. With a PhD in Physics (2022), I bring a unique perspective to solving impactful problems in R&D and business. My expertise lies in synthesizing results quickly and effectively, driving impactful decisions through data-driven insights.

Career

Professional Experience

Tula Health

Senior Data Scientist
Sep 2023 – Present · 2 years
  • Developed and implemented ML pipelines using Neural Network models (CNN, RNN, LSTM, Transformer) and tree-based models (Random Forest, XGBoost, CatBoost) to process noisy biometric data, achieving high predictive performance.
  • Led the advancement of data modeling and preprocessing pipelines, implementing data validation protocols and version control best practices, enhancing pipeline maturity.
  • Ran large-scale experiments to benchmark ML features and models; collaborated cross-functionally on advanced mathematical models for signal processing and predictive analytics in biomarker trends.
  • Utilized AWS services for model deployment, data storage, and processing, ensuring scalable and efficient ML operations.
Data Scientist
Aug 2022 – Sep 2023 · 1 yr 2 mos
  • Advanced analytics, signal processing, and machine learning from wearable data to predict biomarkers.
  • Algorithmic development and data infrastructure for the R&D team.
  • Computational modeling of physiological systems.

Booster Fuels, Inc.

Data Scientist
April 2022 – Aug 2022
  • Designed and executed large-scale experiments using Python and SQL to simulate lifts in KPIs, resulting in improved customer retention.
  • Implemented A/B testing framework using API calls to proprietary algorithms, driving increase in the North Star metric.
  • Developed and maintained data pipelines and reporting dashboards using dbt, Git, and Looker to track user behavior and support product decisions.
  • Conducted in-depth analyses on user engagement and behavior patterns to improve operational efficiency and inform strategic decision-making.

Oak Ridge National Laboratory (ORNL)

Research Assistant — PhD
Aug 2016 – April 2022
  • Applied scientific techniques to analyze complex experimental data, solving a decades-old problem in physics, resulting in 3 technical talks and a publication.
  • Implemented and optimized simulation techniques in HPC environments utilizing GPU and CUDA, enhancing model performance and accuracy.
  • Developed custom data analysis and visualization frameworks in Python to investigate material properties, communicating findings through 2 international conference talks.
Expertise

Skills & Tools

Machine Learning

Neural Networks Tree-based Methods Bayesian Analysis SVM Clustering PCA Autoencoders CNNs RNNs / LSTM Transformers HuggingFace LangChain NLTK

Programming & Tools

Python SQL Bash PyTorch TensorFlow Scikit-learn Pandas PostgreSQL MongoDB dbt Looker Tableau

Cloud & Infrastructure

AWS S3 AWS Lambda SageMaker Redshift GCP Vertex AI Git Docker FastAPI

Transferable Skills

A/B Testing Statistical Analysis Quantitative Modelling Data Engineering Signal Processing Project Management Product Development HPC / CUDA
Work

Projects

Bloodraven — ASOIAF Question-Answering Chatbot

  • Interactive multi-turn RAG chatbot using Gemma/LLaMA via HuggingFace, LangChain, and FAISS; optimized on NVIDIA T4 GPU.
  • Responsive Gradio web interface with real-time, context-aware answers from web-scraped & Wikipedia API data.
Live Demo
RAG LangChain FAISS Gradio HuggingFace

AdTech Product Experimentation Analysis

  • Analyzed an A/B experiment on a new ad product to reduce advertiser overspending and improve resource allocation efficiency.
  • Defined metrics and performed statistical analysis across control & treatment groups, determining a 50% platform revenue lift.
Read on Medium
A/B Testing Statistics Python

AI-Powered Book Recommendation System

  • Personalized recommendation system using GPT4All (orca-mini-3b) and FastAPI; contextual suggestions based on genre, themes, and reading level.
  • Vanilla JS frontend integrated with Google Sites; scalable async backend with CORS middleware.
The Restricted Section
GPT4All FastAPI JavaScript LLM

Customer Churn Analysis at Robinhood

  • EDA on 5,500-user investment portfolio dataset; determined churn rate via statistical and time-series methods.
  • XGBoost churn prediction deployed on AWS SageMaker + API Gateway; F1 score 0.91.
GitHub
XGBoost Random Forest SageMaker AWS

RAGFeynman — LLM Q&A Assistant

  • RAG-based assistant about Feynman's life and teachings using Gemma/TinyLlama, LangChain, FAISS, and HuggingFace.
  • Streamlit interface combining retrieval and generation for accurate, detailed answers.
GitHub
RAG Streamlit FAISS LangChain

Loan Application Prediction

  • Binary classification model on two large loan datasets; XGBoost with F1 score 0.78, deployed via Flask.
  • Outperformed traditional credit-score-based lending models.
GitHub
XGBoost Flask Scikit-learn

ClimbMate — Climbing Buddy Finder

  • Flutter mobile app helping climbers find gym partners via a weighted matching algorithm (gym, skill, schedule, preferences).
  • Real-time matchmaking and connection requests powered by Firebase Firestore & Auth.
Flutter Dart Firebase Firestore

Boulder Beta — AI Bouldering Route Analyzer

  • AI tool that detects climbing holds by color (OpenCV) and generates step-by-step climbing sequences using LLMs (Claude, GPT, Llama).
  • Streamlit interface returns annotated images with numbered holds, limb positions, and natural-language instructions.
OpenCV Streamlit Claude API Ollama

Epiphanies — Swipe-Based Ideas App

  • Mobile-first React Native app delivering one powerful idea at a time from 18+ influential books, with swipe navigation, save, and share.
  • 200 pre-loaded epiphanies across 5 categories; LLM pipeline (Ollama) for automated extraction from books.
React Native Expo Firebase Ollama

Fraud Detection — Financial Transactions

  • EDA and class-balancing on EU credit card transaction dataset from Sep 2013; feature engineering and visualization.
  • XGBoost classifier with F1 score 0.94, deployed on AWS (SageMaker, Lambda, S3).
XGBoost SageMaker AWS Lambda S3
Academic

Education

University of Tennessee, Knoxville

Ph.D. in Physics — Minor in Computational Sciences

M.S. in Physics

IISER Thiruvananthapuram

BS-MS Dual-Degree in Physics

Minor in Chemistry

Endorsements

Testimonials

“

Yadu was a solid asset to our routing team at Booster Fuels, consistently delivering on our data and reporting needs. He showed real initiative, diving deep to understand how our data flowed and using that knowledge to simulate business scenarios that informed strategic decisions around customer retention. What stood out most was his positive attitude and genuine eagerness to learn—I always looked forward to our 1:1s. I truly enjoyed working with Yadu and hope we get to collaborate again.

SD
Sunishchal Dev
AI Safety Researcher at RAND · Research Mentor at Algoverse
“

Yadu has an incredibly powerful, robust mindset and approaches all obstacles with an open mind and a can-do attitude. Despite joining Booster Fuels recently, his contributions as an Analyst were felt immediately. Through his strong technical and written communication skills, Yadu set the bar for analysis reporting and contributed directly toward one of our markets being set on pace for a 33% efficiency improvement. Yadu has an incredibly bright future ahead of him, and I offer the strongest of recommendations based on his technical and emotional intelligence, attention to detail, and infectious positive energy.

MS
Magnus Skonberg
Data Science Manager at Fortegra
“

I have known Yadu for the last three years as a colleague at the Shull Wollan Center at Oak Ridge National Laboratory, and most recently, as a collaborator. During this time, I had the privilege of observing how he led multiple research projects—from implementing state-of-the-art data analysis and developing experimental techniques to troubleshooting and generating new scientific insights from complex data. Though highly self-motivated and capable of working independently, Yadu is a generous team member and collaborator, always willing to support his peers.

DB
Dima Bolmatov, Ph.D.
Incoming Assistant Professor, Texas Tech University

Let’s Connect

Open to opportunities, collaborations, and conversations.

LinkedIn GitHub