AI DEVELOPER / DATA SCIENTIST
I work on tasks of any complexity and domain
01 / Expertise
Corporate RAG systems for search across Confluence, DWH, SQL data marts, PDFs and scans. I separate the offline knowledge pipeline from the online answer flow.
I control versions and access, combine dense and sparse retrieval, narrow a broad candidate pool through LLM reranking, and generate answers only from compact context with mandatory source attribution.
Stack
Stack
Stack
Stack
02 / Blog
Why a neural network can make mistakes in simple calculations and why it needs external tools
Read articleWithin months, SpaceX combined with xAI, monetized Colossus, went public, and agreed to buy Cursor. Here is my reading of Musk’s strategy ahead of a possible AI-market correction.
Read articleA chronological archive of technical articles, notes, and case analyses.
All publications03 / Projects
Employees spent 15–30 minutes searching across fragmented internal sources. In the CorpGPT pilot, this fell to 5–10 minutes.
Manual review of SQL data-mart changes took about 90 minutes. The agent reduced analysis to 35 minutes and helped cut post-release incidents by 35%.
Diagnosing data degradation required manual checks across five sources and took 4.5 hours on average. A stateful agent reduced MTTR to 2.1 hours.
A monthly flow of 20,000–30,000 construction documents required manual transcription. A hybrid pipeline processed about 70% without human intervention.
The complete catalog of detailed engineering case studies and materials.
All projects04 / Contact
Choose a convenient way to get in touch or explore a professional profile.
