👋 Hello, I'm
Yatish Durga
Building intelligent data pipelines and ML systems. Passionate about turning raw data into actionable insights and AI-driven solutions.
Previously worked with
IBM • BeeAI Framework
Open-source AI agents framework — contributed to production codebase
Years Experience
Projects Built
Cost Saved (USD)
Certifications
About Me
The story behind the data
I'm a Data Scientist & AI Engineer with 4+ years of experience turning complex data into intelligent, production-ready systems. My journey started in software development, evolved through data engineering at GAVS Technology, and now spans the full spectrum from building ETL pipelines to architecting RAG-powered AI systems.
I'm currently pursuing my Master's at the University of Central Missouri while interning at IAPP on AI governance frameworks and building AI-driven customer support systems at Saayam For All. I'm also a proud open-source contributor to IBM's BeeAI Framework — one of the leading AI agents platforms.
What drives me is the intersection of data engineering and AI — building the infrastructure that makes intelligent applications possible, then using that foundation to deploy models that actually solve real problems. I care deeply about responsible AI and reducing LLM hallucinations in production.
AI-First Thinking
I approach every data problem by asking how AI can make the solution smarter, faster, and more scalable.
Responsible AI
AIGP-certified — I build with governance, safety, and ethics as first-class requirements, not afterthoughts.
End-to-End Ownership
From raw data ingestion to deployed model — I own the full pipeline and care about production reliability.
Skills & Technologies
Technologies I work with
Programming
Data Engineering
AI / ML
Tools
Work Experience
My professional journey
Data Scientist & AI Engineer
Saayam For All
Oct 2025 – Present · Remote
- Architected a production-grade RAG pipeline to deliver accurate, low-latency AI responses for customer support, significantly reducing LLM hallucinations
- Built end-to-end ETL pipelines to ingest, clean, and index knowledge-base data into a vector store for real-time retrieval
- Developed an AI-powered chatbot that handles user queries with context-aware responses, cutting average resolution time and improving support quality
- Implemented IAM-based access controls and secure data handling practices across the AI infrastructure
Data Science & AI Governance Intern
IAPP
May 2025 – Present
- Design and integration of AI governance frameworks
- Responsible AI development aligned with ethical principles
- Econometric data analysis and statistical methods
- Insights visualized via Power BI dashboards
Research Assistant
University of Central Missouri
Jan 2025 – Present
- Heartbeat classification using ML, LLMs, and Deep Learning
- Data processing, model training, and performance evaluation
- Research on disease detection via smart health data
Data Engineer
GAVS Technology Pvt Ltd
Aug 2021 – Dec 2023
- Optimized GCP and ERP systems — saved $45,000/year
- Built ETL pipelines using Python & SQL
- Cut server storage by 15–20% via smart visualizations
Software Developer Intern
Tensile Tech
May 2021 – Aug 2021
- Frontend development and database integration
- Enhanced UX with HTML/CSS improvements (15% gain)
- Improved version control; reduced data errors by 40%
Education
Academic background
Master's in Data Science & AI
University of Central Missouri, Lee's Summit, USA
January 2024 – December 2025
Advanced studies in Data Science and Artificial Intelligence, focusing on machine learning, deep learning, and data analytics.
Research Assistant: Heartbeat classification using ML, LLMs (Llama), and deep learning — assisting in data processing, model training, and evaluation for disease detection.
Bachelor of Engineering — Mechanical
Gujarat Technological University
2017 – 2021
Completed Bachelor's in Mechanical Engineering with focus on design, thermodynamics, and manufacturing processes. Transitioned into the data & software field post-graduation.
Projects
Things I've built
SQL
Netflix Data Analysis
Trends in movies, TV shows, regional content, and genre popularity using advanced SQL queries.
ML
Mental Health AI Assistant
Personalized mental health support with AI-curated books, videos, and motivational content.
Movie Recommendation System
ML-powered engine that suggests movies based on user preferences and viewing history.
ML
Bike Rental Prediction
Predicting bike rental demand based on weather, temperature, and seasonal factors via regression.
Excel
Sales Dashboard (Excel)
Interactive dashboard with pivot tables, charts, and KPI visualizations for business insights.
Certifications
Professional credentials
AI Governance Professional AIGP
Certified by IAPP in responsible AI governance standards and practices — credential valid Dec 2025 – Dec 2027.
View CertificateDatabricks Fundamentals
Unified data analytics platform combining data engineering, science, and ML on a collaborative workspace.
View Certificate
Google BigQuery
Derive insights from massive datasets using Google's serverless, highly scalable cloud data warehouse.
View CertificateMedium Blogs
Thoughts & insights
What is Prompt Engineering?
The practice of designing and optimizing prompts to effectively communicate with AI models for desired responses.
Read on MediumML Movie Recommendation System
Using machine learning to predict user preferences and deliver personalized movie recommendations.
Read on MediumGet In Touch
Let's build something great together