Hello, I'm
Sneha Murali
AI Engineer & Data Scientist
Computer Science and Engineering student with a strong foundation in data analysis, artificial intelligence and applied machine learning. Completed training programs with Samsung Research and Development Institute, Bangalore on coding, programming, data analysis, and artificial intelligence.
About Me
My Journey & Expertise
I am a dedicated Computer Science and Engineering student specializing in Natural Language Processing (NLP), Deep Learning, and Generative AI. My core mission is to bridge cutting-edge research breakthroughs with tangible, real-world enterprise needs. I focus on developing, training, and deploying advanced models using my primary stack of PyTorch for efficient modeling and Docker for production readiness and scalability.
My experience includes taking high-impact projects from concept to deployment, such as the Arogya-Mitra: Mental Wellness Companion I developed during the Google GenAI Hackathon in 2025. I prioritize strong engineering principles, ensuring that complex models are not only accurate but also scalable, maintainable, and seamlessly integrated into applications using robust MLOps practices.
Core Skills
The Full Stack for AI Development and Deployment
Deep Learning (PyTorch)
Model Development & Training
NLP & Generative AI
Text, Sequence, & LLM Modeling
MLOps & Docker
Model Containerization & Serving
Google Cloud Platform (GCP)
Deployment & Compute Resources
Core ML & Statistics
Scikit-learn, Regression, Classification
Data Engineering
Cleaning, Collection, MySQL
Python Data Stack
Pandas, NumPy, Matplotlib
Visualization & EDA
Seaborn, Power BI, Insight Generation
Featured Projects
Showcasing my best work
Arogya-Mitra
A conversational agent built during the Google GenAI Hackathon in 2025 to provide personalized, non-clinical mental wellness support and resource connection.
IdeaSprint
The ideaSprint is an AI Content Generator which is lightweight web application designed to help marketers and content creators rapidly prototype marketing material.
Normal Deliveries vs C-Section Deliveries
This project analyzes the distribution and frequency of normal (vaginal) vs. C-section deliveries, using two key lenses: 1. Geographical Rate Comparison (Choropleth Maps) 2. Parity-Based Comparison (VBAC Focus)
Get In Touch
I'm currently open to new opportunities.