Comprehensive portfolio of AI research, development, and publications
Research collaboration at Stanford University on optimizing compound AI systems with globally aligned local rewards. Published at ICLR 2026.
Led a team of four delivering applied AI/ML systems for large multinational clients. Designed LLM-based product catalogue translation and developed inventory management and entity matching systems for cross-retailer price comparison.
Selected as Junior Fellow at the American Slovenian Education Foundation. Fellowship program supporting academic excellence and fostering collaboration between Slovenian and American academic communities.
Completed project helping Big Bang leverage the power of AI with their product catalog. Implemented AI-driven solutions to transform their product management and customer experience.
Completed AI implementation projects for Dormeo helping them in their fast growth. Delivered custom AI solutions to enhance their customer experience through advanced technology integration.
Mentored by Stephen Wolfram. Developed multi-agent simulations with Large Language Models and composed a Computational Essay published on Wolfram Community.
AI Intern for Healthcare Applications at Carnegie Mellon University. Worked on AI for Social Good initiative with deployment at IHHN Hospital, Pakistan, mentored by Prof. Rayid Ghani.
Research project focused on predicting impactful events using Graph Machine Learning techniques. Advanced methodologies for event prediction and impact analysis using graph neural networks.
Slovenian adaptation of commonsense reasoning models, extending multilingual commonsense capabilities to Slovenian language with improved cultural and linguistic context understanding.
Participated in Thessaloniki International Forum'21, the 7th International Forum of EYP Greece. Engaged with 170+ young Europeans in discussions about the Future of Europe and societal challenges.
Real-time tracking system for assistive technologies, developed with UCL and UNESCO IRCAI for global accessibility monitoring.
Novel approach to NLP using agent-based models for semantic comprehension with improved interpretability.
Interactive web application for multilingual commonsense descriptions. Deployed after publishing the MultiCOMET paper, supporting 50+ languages.
Machine learning system analyzing research trends to predict emerging breakthroughs 2-3 years in advance.
International Conference on Learning Representations (ICLR 2026)
SiKDD 2025 Conference
SiKDD 2025 Conference
Bachelor's Thesis, University of Ljubljana
Knowledge-Based Systems, Elsevier
EMNLP Findings
Available for research collaborations, AI consulting, and innovative projects