Intelligent Data Deduplication & Clustering Platform
A scalable ML platform that finds and clusters duplicate records, with a feedback-driven retraining loop. Cut duplicates by 80% across a 50K+ document corpus.
Open to full-time, freelance & consulting
Bhargav Patel
Senior Full Stack & Data Engineer
I build scalable Python backends, AI/LLM systems and cloud-native data platforms. 4+ years shipping production software on AWS & Azure.
- Years of experience
- 4+
- Projects shipped
- 10+
- Technologies used
- 60+
- Clients served
- 6+
AI & cloud engineering at scale
I’ve led cross-functional engineering teams from architecture to deployment — designing microservices, ETL pipelines and LLM-powered applications that scale. I specialise in Python backends (Django, FastAPI), cloud-native infrastructure (AWS, Azure) and generative AI using LangChain, LlamaIndex and OpenAI.
Recent work spans data platforms on Microsoft Fabric with Medallion Architecture, machine-learning deduplication systems, real-time analytics dashboards and AI-driven authoring tools. I focus on where cloud infrastructure meets AI — systems that are both intelligent and operationally robust.
02 / work
Selected projects
Showing 10 of 10 projects
Data Platform with Medallion Architecture
A production-grade platform on Microsoft Fabric with bronze, silver and gold layers — delivering reliable, analytics-ready data for enterprise Power BI reporting.
AI-Driven Book Authoring Platform
Lets authors upload, write and update books while generative AI restyles and enhances older content. Multi-agent orchestration reduced production time by 65%.
Data Analytics & Activity Tracking System
Real-time activity tracking that consolidates metadata from many sources, with semantic search and AI-powered duplicate detection in an analytics dashboard.
Sports Data Intelligence Platform
Gives football league agencies real-time data and predictive insights for strategic decisions, powered by ETL pipelines and advanced analytics.
Learning Management Platform
A multi-tenant education platform built from microservices for authentication, administration, content management and safety compliance.
Performance Management System
A SaaS workforce tool combining leave tracking, project management and employee activity modules on secure AWS infrastructure.
Trixi Taxi
A taxi platform for Spain with seamless booking, transparent driver tracking and detailed revenue reports for administrators.
Stroke Prediction
A stroke-risk model using SMOTE oversampling to handle imbalanced data, helping identify high-risk individuals early for clinical intervention.
Play Store Scraping
A scraping pipeline that builds a clean, reliable database of app-ecosystem insights from the Google Play Store.
Work history
From scrapers and APIs to leading AI and data platform teams.
-
Current
Senior Full Stack & AI Engineer
- Architected an LLM-powered authoring platform with multi-agent orchestration (LangChain, LlamaIndex, OpenAI) — 65% faster content production.
- Designed a Microsoft Fabric data platform with Medallion Architecture, PySpark transformations and Power BI dashboards.
- Delivered an ML deduplication engine (TF-IDF + cosine similarity), cutting duplicates by 80% in a 50K+ document corpus.
- Led a cross-functional team through production on AWS (EC2, S3, RDS, CloudWatch) and Azure (AKS, CosmosDB).
-
Previous
Full Stack Developer
- Built a multi-tenant SaaS backend on Django REST and PostgreSQL serving 10K+ concurrent users at 99.9% uptime with Celery + Redis.
- Engineered a real-time React + WebSocket analytics dashboard with sub-200ms latency.
- Set up CI/CD with Jenkins, Docker and Terraform — deployments went from 2 hours to 12 minutes.
- Integrated Stripe, Twilio and AWS SNS for payments, SMS and event-driven workflows.
-
Earlier
Software Engineer
- Developed Scrapy and BeautifulSoup scrapers aggregating data from 200+ sources into MongoDB ETL pipelines.
- Built a GraphQL layer over legacy REST endpoints, reducing over-fetching by 70%.
- Created a server-rendered Next.js storefront, lifting Lighthouse performance from 48 to 92.
Skills & technologies
- Languages
- Python, SQL, JavaScript, TypeScript, HTML, CSS
- Frameworks
- Django, Django REST Framework, FastAPI, React, Next.js, GraphQL
- Generative AI & LLMs
- OpenAI, Gemini, MistralAI, HuggingFace, LangChain, LlamaIndex, ChromaDB, multi-agent systems
- Data engineering
- Apache Airflow, Microsoft Fabric, Medallion Architecture, PySpark, DuckDB, Streamlit, Power BI
- Cloud & DevOps
- AWS, Azure, Docker, Terraform, Jenkins, CI/CD, CloudWatch, IIS
- Databases
- PostgreSQL, MySQL, MongoDB, DynamoDB, Redis, OpenSearch, CosmosDB, Elasticsearch
- Data science & ML
- Scikit-learn, NumPy, Pandas, Matplotlib, Seaborn, statistical analysis, predictive modelling
- Other tools
- Celery, RabbitMQ, WebSocket, microservices, Scrapy, BeautifulSoup, webhooks, Twilio
2018 – 2022
B.E. Computer Engineering
Aditya Silver Oak Institute of Technology · First Class with Distinction
2021
GATE — Computer Science
IIT Bombay / MHRD · All India Rank 9,081
2020
NPTEL — C Programming
IIT Kharagpur · ELITE grade
05 / contact
Let’s build something great
Available for full-time roles, freelance projects and consulting — especially AI-augmented products and data platforms.