Open to new opportunities
Yugesh B
Data Engineer building automated pipelines, GenAI assistants, and large-scale scraping systems. Based in Chennai, Tamil Nadu, India.
About
From Perl automation to GenAI products
A quick look at how the journey connects.
Data Engineer with 4+ years across web-scraping automation, ETL/data pipelines, and GenAI-powered applications. Started in Perl-based publishing automation, moved through large-scale e-commerce scraping and Bloomberg financial data engineering at TCS, and now builds data infrastructure and AI-assisted tooling at Thurro. Comfortable owning a problem end-to-end — from a raw HTML page or PDF to a production pipeline or a working LLM-backed product.
Current Role
Data Engineer @ Thurro
Location
Chennai, Tamil Nadu, India
Education
BCA, Computer Programming & Applications
Career
Experience
Click a role to expand contributions and tech stack.
Data Engineer
Dec 2025 — Present
- —Building and maintaining data engineering pipelines and analytics infrastructure across internal reporting and data-store systems.
- —Working with database and reporting tooling spanning structured storage and analytical querying.
Toolbox
Skills & Technologies
Organized by category — every item here has shipped in a real project.
Languages
Web Scraping & Automation
Databases
AI / GenAI
Data & Visualization
Cloud & Tooling
Practices
Case Studies
Featured Projects
Two production systems I built and maintained end-to-end.
Indian Law AI Chatbot
Streamlit-based legal Q&A assistant with a self-refreshing case-law dataset and multi-key LLM failover
A production Streamlit chatbot that answers questions on Indian law — the Bharatiya Nyaya Sanhita, Bharatiya Nagarik Suraksha Sanhita, Bharatiya Sakshya Adhiniyam, the Constitution of India, and case law from the Supreme Court and all 24 High Courts — grounded in a 20,700+ entry curated Q&A dataset built by parsing raw legislative text and court judgments. Streams Gemini responses with automatic multi-key failover, renders LLM-generated charts inline, and keeps its dataset current via a fully automated daily GitHub Actions pipeline.
20.7K
Q&A Dataset Entries
24+
Courts / Tribunals Tracked
3
Scraper Sources
3.3K
Lines of Python
Language breakdown (live from GitHub)
Key Contributions
- Streaming chat engine with multi-key API failover — round-robin Gemini API key rotator with quota-aware failover, exponential backoff, and auto-continue logic that transparently resumes responses cut off by output-token limits.
- Self-refreshing legal dataset via GitHub Actions — a daily cron workflow pulls new Supreme Court, High Court, and tribunal judgments from Indian Kanoon's official RSS feeds and auto-commits new entries with no manual upkeep.
- Offline regex-based Q&A extraction pipeline — parses raw statutory text directly into 20,000+ structured Q&A pairs with no LLM calls, plus a secondary LLM-assisted extraction path for judgment text.
- Multi-source legal web scraping across three independent sources, each normalized into one unified Q&A schema.
Automated Document Intelligence Pipeline
Multi-engine web scraping & dual-database data pipeline for financial/regulatory disclosure documents
A production data-collection system that scrapes portfolio holdings, factsheets, insurer newsletters, and regulatory (RBI/SEBI) filings from 229 site-specific configurations spanning mutual funds, banks, insurers, and regulators — normalizing, deduplicating, and loading results into a dual-database (MySQL + ClickHouse) pipeline with automated S3 archival. Built and maintained end-to-end across ~29,000 lines of Python.
229
Site Configs
3
Scraping Engines
2
Databases
~29K
Lines of Python
Key Contributions
- Config-driven scraping framework processing 229 distinct site sources from a single unified codebase, eliminating per-site custom scripts via declarative YAML configuration.
- Multi-engine fallback scraping chain (Selenium → Playwright → static HTTP) that escalates to heavier browser automation only when a lighter engine fails.
- Dual-database persistence layer (MySQL + ClickHouse) with automated staging tables, cross-database sync, and a date-validation quarantine system for ambiguous or invalid dates.
- LLM-based fallback date-resolution mechanism (via Ollama) as a last-resort recovery step before any record is quarantined.
Credentials
Certifications
Salesforce Certified Administrator (SCA)
Salesforce
Credential link coming soonPython
LinkedIn Learning
Credential link coming soonData Science (Machine Learning)
LinkedIn Learning
Credential link coming soonTestimonials
What colleagues say
This section is reserved for real feedback from managers and teammates — nothing fabricated in the meantime.
Manager testimonial
Coming soon
Colleague testimonial
Coming soon
Mentor testimonial
Coming soon
Resume
Full Resume
View inline or download the PDF.
Get in touch
Let's build something
Open to Data Engineering, Python automation, and GenAI application roles.