Skip to content
View KevinHCH's full-sized avatar
🎯
Focusing
🎯
Focusing
11 followers · 49 following

Achievements

Achievement: Pull SharkAchievement: Arctic Code Vault Contributor

Achievements

Achievement: Pull SharkAchievement: Arctic Code Vault Contributor

Block or report KevinHCH

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.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

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

Report abuse
KevinHCH/README.md

Kevin Herbas | Backend & AI Engineer | RAG, Automation, Scraping

I design and build production-ready backends and applied AI systems. My work focuses on turning messy data into structured intelligence and creating automation pipelines that actually scale.

  • Reduced product compliance checks from 2 weeks to under 1 minute with AI
  • Automated discovery and analysis of 10k+ EU procurement tenders daily
  • Delivered fullstack scrapers and dashboards powering 120k+ listings per week

🚀 Highlight Projects

  • 🛡 Compliance AI Product Validator - Automated PDF & image checks with instant reporting
  • 🌍 Vitellus - European procurement intelligence platform with AI-powered insights
  • 🕷 KRAVEN - Scrapy + Django fullstack job scraper and dashboard
  • 🎨 Charis CLI - Open-source Gemini CLI for image generation and editing

More details and case studies available in pinned repositories.

💡 Technical Philosophy

I don't just build prototypes - I focus on production systems with monitoring, retries, and scalability. Most client work is private, but my public repos show how I approach backend engineering, RAG pipelines, and AI-powered automation with clean, maintainable code.

🛠 Core Tech Stack

  • AI & LLMs: OpenAI, Google Gemini, Mistral, Anthropic Claude
  • Orchestration: LangChain, LangGraph, PydanticAI, Llama-Index, custom pipelines
  • Backend: Python (FastAPI, Django, Flask), Node.js/TypeScript, Bun
  • Data: Supabase/Postgres (pgvector), Redis, FAISS
  • Cloud & Infra: AWS (Lambda, ECS, EventBridge, S3), Docker, CI/CD pipelines
  • Scraping: Playwright, Puppeteer, Scrapy

🎯 Focus Areas

  • RAG pipelines and AI-powered assistants
  • Data scraping & automation at scale
  • Backend APIs and cloud architecture
  • Compliance and procurement intelligence systems

🤝 Let's Build Something

Looking to integrate AI into real-world products? Check my Upwork profile or reach out on kevinherbas.com.

Pinned Loading

  1. vitellus vitellus Public

    Complete backend system for European procurement intelligence that automatically scrapes and analyzes government contracts from the official EU tender database (TED). Built with TypeScript, AI proc…

    TypeScript 2 3

  2. charis charis Public

    Charis is a command-line tool built with Bun + TypeScript that integrates Gemini through the Vercel AI SDK for image generation and editing.

    TypeScript

  3. kraven kraven Public

    Kraven it's a tool to monitor and scrape upwork jobs based in the personal criteria of each user

    Python 1

  4. compliance-ai-product-validator compliance-ai-product-validator Public

    AI-powered compliance validator built for a client to automate product certification checks. Processes PDFs and images with LLMs (OpenAI, Gemini, Mistral), validates tests and visuals, and generate…

  5. crawling-example-freelance crawling-example-freelance Public

    Python

  6. research-agent-llama research-agent-llama Public

    Python