Hi, I'm Yash Patil
Building intelligent systems that transform data into actionable insights. Specializing in AI/ML, LLMs, and Semantic Retrieval Systems.
About Me
Experience
Education
M.S. Computer Science
Santa Clara University
Experience
3+ Years in
AI/ML & Data Science
Projects
20+ Completed
Projects
I'm a passionate AI/ML Engineer and Data Scientist with expertise in building intelligent systems that solve real-world problems. Currently at Tip Top Technologies, I'm shipping low-latency AI services on Kubernetes/AWS, building semantic retrieval systems handling 2M+ queries/day, and developing agentic meeting copilots with multi-agent architecture.
With an M.S. from Santa Clara University, I've worked across companies like Searchspring and Anju Software, where I built scalable data pipelines serving 1400+ clients and improved efficiency by 45%. I specialize in RAG systems, vector databases (FAISS, Pinecone), and LLM applications.
Skills & Technologies
AI & Machine Learning
Vector Databases & Retrieval
Programming Languages
Data Engineering
Cloud & DevOps
Visualization & Tools
Work Experience
AI/ML Engineer
Tip Top Technologies
- Shipped low-latency AI services on Kubernetes/AWS, improving NDCG@10 by 15%
- Built FAISS + Pinecone semantic retrieval system handling 2M+ queries/day
- Reduced p95 latency from 120ms to under 50ms through optimization
- Building agentic meeting copilot with voice interface using multi-agent architecture
AI Intern
Samvid
- Built LLM evaluation pipelines benchmarking GPT-4o, Gemini, Claude, and Llama 3.1
- Developed automated testing frameworks for LLM response quality
- Implemented RAG systems for document processing workflows
Data Scientist (Student Assistant)
Santa Clara University
- Led Workday Student platform transition with advanced ETL processes
- Applied data science expertise to optimize university operations
- Built predictive models for student success initiatives
Data Engineer
Searchspring
- Implemented spell correction system serving 400+ clients
- Built PySpark big data pipeline processing data for 1400+ clients
- Optimized search algorithms improving user experience significantly
Data Scientist Engineer
Anju Software
- Developed TA-Scan 7, achieving 45% efficiency improvement
- Launched DATA API serving multiple enterprise clients
- Mentored team members in PySpark, PyTorch, and Python
AI Intern
MarQuery
- Integrated Twilio API for automated communication systems
- Developed AI chatbot for e-commerce platform
- Implemented NLP solutions for customer support automation
Featured Projects
Databricks Agent Smart Merge
AI-powered merge reducing notebook conflicts by 60% for data science teams using context-aware cell analysis.
Multi-Agent Chatbot Application
Multi-agent system achieving 40% faster response resolution through parallel LLM orchestration and task routing.
Agentic RAG with LlamaIndex
RAG pipeline with 95% retrieval accuracy across 10K+ documents using hybrid search and agentic reasoning.
GPT from Scratch
124M parameter GPT implementation with custom tokenizer, trained from scratch on 8GB text corpus.
Resume Database Chatbot
Local LLM-powered chatbot for intelligent resume parsing and candidate matching from databases.
Smart ATS System
Intelligent Applicant Tracking System built with Streamlit for resume screening and candidate evaluation.
AI Job Platform
Full-stack job platform with AI-powered matching and recommendation system for candidates and employers.
ML & AI Chatbot
NLP-powered chatbot for student complaint registration and college information with automated responses.
AI Email Generator
Intelligent email generation tool using AI for professional communication automation.
Multi-Agent System
Framework for building and orchestrating multiple AI agents working collaboratively on tasks.
Reinforcement Learning
Advanced reinforcement learning implementations for training intelligent agents in various environments.
Pollution Notifier
Android application for real-time pollution monitoring and notifications for environmental awareness.
Search & Games AI
Implementation of AI search algorithms and game-playing agents using various optimization techniques.
Bulk Email Sender
Automated email distribution system for sending personalized bulk emails efficiently.
ML Mastery Projects
Comprehensive machine learning projects covering end-to-end ML pipeline implementations.
Python Guide
Comprehensive Python programming guide with best practices and advanced concepts.
Certifications
Microsoft Azure for Data Engineering
Microsoft
Complete Machine Learning & Data Science
Bootcamp Certification
AI For Everyone
Coursera / DeepLearning.AI
Introduction to Python for Data Science
DataCamp
Contact Me
Have a project in mind or want to collaborate? Feel free to reach out!
Location
San Francisco Bay Area, CA