Applied AI
AI integration, RAG & local models
Designing and building AI systems as a product: RAG pipelines, processing in a controlled environment, and sizing compute infrastructure.
This area is different from AI as a development tool: there, AI helps me write code; here, AI is what gets built.
Document system with RAG
At a current project I design and build a document AI layer focused on ingestion, semantic indexing, and information retrieval. The solution integrates with the main application through decoupled services.
Privacy and data control
The architecture prioritizes processing within a controlled environment and protecting sensitive documentation, reducing external dependencies where the context requires it.
Infrastructure evaluation
I evaluate compute capacity, memory, context size, and model type to size a balanced solution based on load and product requirements.
Product-driven design
The design always starts from real business needs — what documentation needs querying, how often, under what privacy requirements — before deciding on the technical architecture.
Want to see it in detail?
Download the resume focused on applied AI, in PDF.