Skip to content

Adarsh-Raj04/Adarsh-Raj04

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

11 Commits
 
 

Repository files navigation

Hey, I'm Adarsh Raj 👋

< DATA & AI ENGINEER />

Architecting enterprise-scale data and AI systems at GSK

LinkedIn Portfolio Email GitHub


🧠 About Me

I'm a Data & AI Engineer with 2+ years of experience at GSK (GlaxoSmithKline), building intelligent, enterprise-scale systems across metadata management, data governance, and AI-powered search.

I own the full engineering lifecycle — from designing semantic search with OpenAI & Azure AI Search, to shipping Apache Spark pipelines on Databricks, to building FastAPI microservices and enterprise integrations with ServiceNow, Collibra, and SailPoint.

  • 🔭 Currently building AI-powered metadata and governance platforms at GSK
  • 🤖 Passionate about LLMs, semantic search, and intelligent automation
  • 🛠️ I own end-to-end: architecture → backend → DevOps → delivery
  • 🌱 Exploring Databricks Genie (NLQ) and NLP-driven analytics
  • 🏆 Eliminated 90% manual effort and saved ~200 hours/year through automation
  • 📍 Based in Bengaluru, India — Silicon Valley of India

📊 Impact at a Glance

Metric Result
Manual effort eliminated 90% (~200 hrs/year saved)
Data sync time reduction 99.6% (30 min → 7 sec)
Metadata retrieval improvement 87.5% (8 hrs → 1 hr)
Tutorial views 50K+ developers reached

🚀 Enterprise Projects

🔍 Rover — Semantic Search & Conversational AI Platform

OpenAI · Azure AI Search · FastAPI · Python

Designed and implemented enterprise-scale semantic search and conversational query capabilities for the Rover metadata platform at GSK. Metadata assets are now discoverable via natural language, powered by OpenAI embeddings and Azure AI Search.


⚡ ServiceNow–Collibra Governance Automation

ServiceNow · Collibra · Azure Function Apps · GraphQL · Python

End-to-end integration automating governance workflows between ServiceNow and Collibra — eliminating 90% of manual effort (~200 hrs/year) and achieving a 99.6% reduction in data sync time (30 min → 7 sec).


🔥 Spark Metadata Ingestion & Cataloguing Pipelines

Apache Spark · Databricks · Azure Data Factory · Delta Lake

Owned development and optimisation of Spark-based ingestion pipelines on Databricks, achieving significant runtime reductions and automating metadata cataloguing across enterprise systems. Integrated DQ outputs into Collibra for transparent governance reporting.


🛠️ Tech Stack

AI & Search

OpenAI Azure AI Search Semantic Search NLP Power BI NLP

Data Engineering

Apache Spark Databricks Azure Data Factory Delta Lake PySpark

Backend & APIs

Python FastAPI GraphQL REST APIs Java

DevOps & Cloud

Azure DevOps GitHub Actions Docker Azure Function Apps CI/CD

Enterprise Integrations

Collibra ServiceNow SailPoint


🎓 Education

B.Tech — Computer Science & Information Science Engineering M.S. Ramaiah University of Applied Sciences, Bengaluru | 2020–2024 | CGPA: 8.2/10.0


🏅 Certifications

Certification Issuer Link
Career Essentials in Generative AI Microsoft & LinkedIn Link
Machine Learning with Python Cognitive Class Link
SQL (Advanced) HackerRank Link
Introduction to Cybersecurity Cisco Link
Python Masterclass Udemy Link
Build Smarter, Scalable Al Agents with UiPath GeeksforGeeks Link

🏆 Achievements

  • 🥇 Best Project Award — out of 250 students at M.S. Ramaiah University
  • 🎯 Rank 5 on GeeksforGeeks at university level
  • 🏁 Rank 281 in GFG Coding Contest 119
  • 📺 50K+ views on web development tutorial

📈 GitHub Stats

GitHub Streak

GitHub Activity Graph


"Turning data into intelligence, one integration at a time"

Profile Views

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors