Hello, I'm
Sanket Muchhala
AI/ML Engineer
I build AI that ships. MS in Data Science from Indiana University Bloomington.
About
AI/ML Engineer with 3+ years of experience building scalable solutions using generative AI, LLMs, and NLP.
I specialize in designing agentic systems, document intelligence workflows, and ML pipelines deployed at scale. My work spans insurance, esports, and enterprise analytics, from research and development to production deployment of AI systems that make real-world impact.
Technologies & Tools
Python
SQL
R
JavaScript
TensorFlow
PyTorch
Scikit-learn
FastAPI
MLflow
SpaCy
GPT-4
LangChain
RAG
Agentic AI
Vector DBs
NER
Text Classification
Summarization
Sentiment Analysis
Pandas
NumPy
PySpark
AWS
Azure Data Lake
Azure SQL
Tableau
Power BI
R Shiny
Education
MS in Data Science
Indiana University Bloomington Aug 2022 – May 2024Machine Learning, Deep Learning, NLP, Computer Vision, Applied Database Technologies, Data Mining
B.Tech in Computer Engineering
Thakur College of Engineering & Technology Jun 2017 – Jun 2021Data Structures, Algorithms, Database Systems, Operating Systems, Computer Networks
Experience
AI Engineer
Progressive Insurance May 2024 – Present- Engineered custom NLP and CV models using TensorFlow and PyTorch to process and classify claim-related texts, forms, and images
- Built ML pipelines with Apache Airflow and Azure Data Factory for streaming data from SQL Server and Azure Data Lake
- Deployed models to production using Azure ML Services; managed versioning with MLflow and DVC
- Achieved 35% reduction in manual claim processing time and improved fraud detection accuracy by 25%
Research Assistant, Generative AI
Indiana University Bloomington Dec 2023 – May 2024- Improved transcript accuracy by 18pp using a GPT-4 RAG pipeline deployed on BigRed200, processing 200+ hours of esports videos
- Reduced latency 40% in chat feature via GPT-4 sentiment analysis microservice, processing 1M+ messages in near real-time
- Automated retraining pipelines using SLURM on HPC systems, cutting manual ETL effort by 6 hours per match
Data Analyst
IBM Sep 2020 – Jun 2022- Led end-to-end development of a churn prediction model using Python and Scikit-learn, driving a 20% reduction in customer attrition
- Refactored ETL workflows using Azure Data Lake and SQL, improving data availability and cutting processing time by 15%
- Deployed ML models to Azure ML environments with CI/CD support, accelerating release cycles by 25%
Featured Projects
kemlang.cloud
LiveA polished AI-powered language learning platform focused on practical learning flows, interactive study, and modern web delivery.
raichu.live
LiveA live, interactive web project built with a fast product-focused interface, clean deployment, and real user access through a dedicated domain.
languagelineage.org
LiveA language exploration platform that presents linguistic relationships, history, and discovery through an accessible web experience.
funnynews.club
LiveA modern, AI-powered news aggregation platform that discovers and curates the funniest, most absurd news stories from across the internet.
Other Projects
Litigation workflow agent demo with a multi-agent orchestration pipeline. Features hybrid RAG retrieval, citation verification, adversarial review, and eval scoring.
An open-source AI simulation engine for B2B founders. Simulates Go-To-Market strategies using Mirofish swarm intelligence to test messaging against buyer personas.
A monetized prediction API powered by the MiroFish swarm intelligence engine. Spawns multi-agent simulations where diverse AI agents debate and collectively predict outcomes.