Data Scientist • AI Systems Architect • ML, NLP, LLMs & Scalable Data Engineering

I build production-grade AI systems that transform messy, multi-source data into real-time intelligence, automation, and decision-ready insights.

My work blends ML, NLP, LLMs, large-scale scraping, enrichment architectures, and agentic automation to design AI products that actually ship — not just experiments.

I specialize in:

• 🕸️ Universal scraping systems across 50+ dynamic, anti-bot-protected websites
• 🧩 Multi-source data enrichment engines integrating 20+ APIs with waterfall logic
• 🧠 LLM-powered extraction & automation workflows
• ⚙️ High-uptime data pipelines & research intelligence platforms
• 📡 Production APIs & real-time enrichment services

• AI Systems Architecture
  End-to-end workflows, LLM automation, intelligent extraction, decision systems

• Universal Web Scraping
  Playwright/Selenium-based scrapers for dynamic JS, forms, pagination, bot protection

• Multi-Source Data Enrichment
  Apollo, PDL, ContactOut, SimilarWeb, Enrich.so, custom API routing & fallback pipelines

• LLM-Driven Data Workflows
  Classification, entity extraction, topic mapping, lead intelligence generation

• Scalable Data Engineering
  FastAPI services, data validation, auto-retry systems, queue-based workflows

• Product & Team Leadership
  Led global teams across India, Hong Kong, France & the US

(Hong Kong — Remote)

At KurationAI, I built the foundational intelligence layer powering:

• 🌐 A universal web scraper deployed across 50+ global sources
• 🔗 A 20+ API enrichment engine with waterfall failovers, retries & key rotation
• 🧠 LLM-based classification & extraction pipelines
• 🔎 Similarity-search-driven lead intelligence datasets
• ⚡ Production-grade FastAPI services for real-time enrichment

Stack: Python, Playwright, Selenium, FastAPI, LangChain, MongoDB, RSS aggregation, GPT/Claude/Perplexity APIs

Built org-wide data strategy, BI platform, ML operations, and scalable pipelines.

Optimized expert-matching using NLP, automation, search & scalable data workflows.

Built Infosphere, an NLP-powered research engine using 15+ extracted attributes.

Customer segmentation, forecasting, sentiment analysis.

Built a university developer community; delivered technical workshops.

Interactive visualization systems using D3.js, Node.js, MongoDB.

• M.Sc. Data Science & AI — IISER Tirupati (2025–2026)
• International Exchange — ISEP Paris (Data Science & Big Data Analytics)
• B.Tech Computer Science Engineering — Alliance University

• 🏅 Winners — Philips Digital Healthcare Conclave 2015
• 🧠 Built intelligence platforms integrating 100+ data sources
• 📝 Research in neural-symbolic topic evolution & text analytics
• 🥇 Multiple Best Speaker awards

• ⚡ Universal AI Web Scraper — Dynamic JS, anti-bot, forms, pagination
• 🔗 Multi-Source Enrichment Engine — 20+ APIs with smart fallback
• 🔍 Infosphere — NLP-driven research engine with Algolia
• 🚫 LLM-Powered Toxic Comment Classifier
• 🤖 Automated Lead Intelligence Platform

➡️ Check pinned repositories for demos & code.

• GitHub activity and contribution statistics available on demand
  → View live GitHub stats

• Language usage breakdown
  → View top languages

I’m always open to collaborating on AI systems, enrichment engines, LLM automation, scalable pipelines, or research intelligence tooling.
Let’s build something impactful.