Senior Full Stack Engineer building AI-powered products.
I design and ship production systems end to end — from backend services and data pipelines to the UI — and these days most of my work is about bringing LLMs into real applications. My background in knowledge graphs, semantic technologies and text mining gives me a solid foundation for retrieval, search and making unstructured data useful.
- LLM integrations — embedding models like GPT and Claude into production apps, with prompt design, structured outputs and evaluation
- RAG & semantic search — retrieval pipelines, embeddings, vector search and hybrid search on top of Elasticsearch / PostgreSQL
- AI agents & tool calling — multi-step workflows where models use APIs, data sources and internal tools
- AI-assisted engineering — using AI tooling to speed up the development process for myself and my teams
AI / ML
Backend
Frontend
Data & Messaging
DevOps & Tooling
Before LLMs went mainstream, I worked on semantic publishing and knowledge extraction from scientific literature — knowledge graphs, ontology-based text annotation and text mining.
Show publications (5)
-
Infrastructure and Population of the OpenBiodiv Biodiversity Knowledge Graph — Biodiversity Data Journal, 2021 A linked open knowledge graph combining knowledge extracted from academic literature with the GBIF taxonomic backbone, modelled with the OpenBiodiv-O ontology. doi:10.3897/BDJ.9.e67671
-
The Pensoft Annotator: A new tool for text annotation with ontology terms — BISS, 2020 A tool that maps free text to concepts from recognised ontologies, making content machine-understandable. doi:10.3897/biss.4.59042
-
Semantic Publishing Enables Text Mining of Biotic Interactions — BISS, 2020 Extracting species interactions from semantically tagged (XML) scholarly articles, in collaboration with GloBI. doi:10.3897/biss.4.59036
-
Streamlined Conversion of Omics Metadata into Manuscript Facilitates Publishing and Reuse of Omics Data — BISS, 2020 Turning omics dataset metadata into peer-reviewed data papers to improve data quality, discoverability and reuse. doi:10.3897/biss.4.59041
-
OpenBiodiv: Linking Type Materials, Institutions, Locations and Taxonomic Names Extracted From Scholarly Literature — BISS, 2019 Using RDF and semantic queries over 729M+ statements to answer complex questions across literature sources. doi:10.3897/biss.3.35089
Co-authors: Mariya Dimitrova, Teodor Georgiev, Lyubomir Penev, Viktor Senderov, Jorrit Poelen, Donat Agosti, Raïssa Meyer, Pier Luigi Buttigieg, Seyhan Demirov, Vincent S. Smith.
- Master's degree — Computer Software Engineering
- Bachelor of Engineering — Automation Engineering Technology