m
miletskyi

Sergii M

@miletskyi

Python AI developer, over 12 years in IT, document AI and RAG in production

Ukraine
Ukrainisch, Englisch
Einige Informationen werden in englischer Sprache angezeigt.
Über mich
12+ years in IT, founder of Cloverity. Up to 98% accuracy extracting SEC 10-K/10-Q statements from PDFs. A 44K-line PHP backend moved to Python FastAPI with 918+ tests. I build Python and AI systems that read hard documents (contracts, tenders, financial filings) and return answers you can check, with citations. In production, not demos: a tender-analysis SaaS, live since 2025. You own the code and the data: your repository, your server, NDA on request. Send me 2-3 sample documents and I will tell you what is possible.... Mehr lesen

Kompetenzen

m
miletskyi
Sergii M
offline • 
Durchschnittliche Antwortzeit: 1 Stunde

Meine Dienstleistungen

KI-Integrationen
I will extract data from PDF and scanned documents to excel or json with ai ocr
Entwicklung von KI-Chatbots
I will build a rag ai chatbot that answers from your pdfs with source citations

Portfolio

Arbeitserfahrung

Porkbun_LLC

Founder & CEO

Porkbun LLC • Selbstständig

Jun 2026 - Present • 4 mos

After years of building AI systems for clients, I'm going all in as CEO of Cloverity - my own company, focused on document intelligence and custom AI agents.

Capgemini

Capgemini

Vollzeit • 5 yrs

Senior Software Engineer / Team Lead

May 2022 - Jun 2026 • 4 yrs 1 mo

Senior Software Engineer and Team Lead on AI and backend projects. Built an LLM gateway PoC in front of AWS Bedrock (LiteLLM Proxy, PostgreSQL, Langfuse) to control LLM costs and usage across teams. Migrated a ~44k-line PHP application to Python/FastAPI and React using Claude Code agents. Built from scratch an AI translation and document-processing microservice on Azure OpenAI, and led a team of 10 on an automotive web service.

Team Lead

Jun 2021 - May 2022 • 11 mos

Led teams of 4-7 engineers on healthcare projects: a Patient Portal (Python, Django, GraphQL, React) with 86%+ unit test coverage and a broker-commission calculation platform. Also delivered an app that receives and displays geo-coordinates, photos and addresses (Python, Django, Telegram API).