Jackey C.

Data & AI Solutions Engineer | Lead Generation & Web Data I build data pipelines and AI-powered tools that turn messy public web data into clean, decision-ready assets — and when it makes sense, into RAG-powered agents that answer questions from that data. What I solve: • Lead Generation at Scale — prospect databases with verified contacts (names, emails, phones, LinkedIn), enriched and deduplicated, ready for your sales team. • Market & Competitive Intelligence — pricing monitoring, product catalogs, review mining, market research. • Document Intelligence — parsing complex PDFs (tables, formulas, mixed-language) into structured Excel/CSV, and into chunked, embeddable formats for RAG. • AI Agents & RAG Pipelines — knowledge-base Q&A agents (WhatsApp, web, internal tools) on vector databases; document ingestion → chunking → embeddings → retrieval → LLM answer, with moderation and audit layers. • Anti-Bot & Hard Targets — Cloudflare, AWS-WAF, aggressive rate limiting: I know when to engineer around it and when to tell you it's not worth it. How I work: • Feasibility-first: I tell you what's realistic before you commit — including when the answer is "don't do this." • Accuracy over volume: every record is verified or clearly flagged. No fabricated data, ever. • Documented & reusable: scripts, schemas, pipelines you can run again without me. • AI done right: generated content is moderated and human-reviewed — I don't ship hallucination-prone outputs. Selected outcomes: • Built a 50,000+ record physician directory from publicly available health registries, deduplicated and URL-verified — delivered as a structured database for client's internal use. • Processed 60,000+ facility records (clinics, hospitals, labs) from an open government registry, with ~85% phone and ~75% email completeness — cleaned, normalized, and export-ready. • Extracted 15,000+ product reviews from a Cloudflare-protected e-commerce site in 3 days with dual-pass validation. • Delivered a 5,000+ record Google Maps enrichment pipeline (phone/website/email matching, 23-28% verified-match rate). • Processed formula-heavy, bilingual PDFs into structured Excel — eliminating days of manual re-entry. Skills: lead generation, prospect list, B2B data, list building, contact enrichment, data scraping, web scraping, Python, Playwright, Selenium, API integration, RAG, vector databases, PDF parsing, data cleaning, data mining, market research Languages: Fluent English & Chinese. Message me with your use case. I'll reply within 24 hours with a feasibility assessment and a realistic plan — including what I can't do, so you never waste budget on false promises.