Hi! I am a software engineer specializing in scalable web scraping, data harvesting, and LLM-powered automation pipelines. My goal is to bridge the gap between raw web data and structured database-ready intelligence.

---

• Intelligent Data Extraction: Implementing state-of-the-art LLMs (like Google Gemini and OpenAI GPTs) to parse raw, messy text into strictly validated JSON formats.
• Scalable Scraping Pipelines: Designing custom scrapers for e-commerce, real estate, financial tech, and corporate intelligence.
• No-Code / Low-Code Integrations: Connecting complex scraping systems directly into automation stacks like n8n, Make (Integromat), and Zapier.

---

• SmartSchema Extract : Convert any unstructured text (invoices, emails, PDFs, HTML) into strictly validated JSON using Gemini's native Structured Output. No hallucinations, no complex regex.

---

• Languages: JavaScript (ES6+), Node.js, Python, HTML/CSS.
• Frameworks & Libraries: Hono, Apify SDK, Crawlee, Puppeteer, Playwright.
• Infrastructure: Cloudflare Workers, Docker, AWS.
• AI Integration: Google AI Studio (Gemini), OpenAI API, LangChain.

---

Need a custom scraping actor, a specialized LLM parser, or help integrating Apify data into your internal API?

• GitHub: github.com/sergiocalvog 
• Support: Feel free to open an issue on the actor's Q&A section or contact me directly through my GitHub profile.