Skip to content
View souvik79's full-sized avatar
🏠
Working from home
🏠
Working from home

Block or report souvik79

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
souvik79/README.md

Souvik Basu

AI, Data & Platform Engineering Lead · Founder & Architect, UPSC Zone AI

I design and deliver production-grade AI, data and cloud platforms that turn complex business workflows into reliable, scalable systems. Across 20 years in software engineering and architecture, I have led backend modernisation, enterprise integrations, data platforms and applied-AI delivery.

My focus is senior technical leadership: shaping architecture, reducing delivery risk, guiding engineering teams and staying close enough to implementation to make sound decisions.

Current focus

  • Agentic AI and workflow automation
  • Retrieval-Augmented Generation and vector search
  • Multi-provider LLM platforms, governance and observability
  • Data ingestion, transformation and publishing platforms
  • Cloud-native architecture across AWS and Google Cloud
  • AI-native engineering with Claude Code and Codex

Selected work

UPSC Zone AI — Founder & Architect

Building an independent AI learning platform for civil-service preparation. The platform combines vector-based RAG, grounded answers with source attribution, document ingestion, semantic retrieval and cloud deployment on Google Cloud.

AI Gateway

Architected a provider-neutral gateway for routing, policy enforcement and operational visibility across multiple LLM providers, giving product teams one governed integration surface.

Data Manager

Designed a data integration and publishing platform that ingests heterogeneous sources, applies validation and transformation pipelines, maintains curated datasets and distributes them to downstream products.

Intelligent Data Acquisition Platform

Built resilient, monitored acquisition pipelines with browser automation, extraction, normalisation, retries and quality controls for high-volume multi-source data workflows.

Document Intelligence & RAG

Developed document-question-answering workflows spanning PDFs, office documents, images and web content using vector retrieval, hybrid search, OCR, multimodal models and source attribution.

Technology landscape

Python FastAPI Node.js Laravel REST APIs Microservices
LLMs RAG Vector Databases LangChain MCP OpenAI Claude
AWS Google Cloud Docker Kubernetes CI/CD
Data Engineering ETL/ELT MySQL MongoDB Observability

Connect

Architecture first. AI-native delivery. Measurable business outcomes.

Popular repositories Loading

  1. document-q-n-a document-q-n-a Public

    Production-ready RAG application for intelligent document understanding using multimodal AI, vector search and LLMs.

    Python 3

  2. Scraper-AI Scraper-AI Public

    AI-powered web scraping framework using LLMs and SLMs for intelligent extraction, structured data generation and automation workflows.

    Python 1

  3. ring-tool ring-tool Public

    Python 1

  4. diskdoctor diskdoctor Public

    🩺 Self-running monthly macOS disk-space report with AI-categorized cleanup (safe-to-delete / review / keep). Report-only.

    Shell 1

  5. flux-image-generator flux-image-generator Public

    AI Image generator using flux HF LLM model

    Python

  6. souvik-basu souvik-basu Public

    HTML