Matej Kalc Full-Stack AI Engineer. Ideas into products.
I’m based in Trieste, engineering AI at NLB (opens in new tab) and founding Timeo (opens in new tab). I balance model quality, latency, and cost under real business constraints.
- RAG and evaluation
- Agent orchestration
- LangGraph workflows
- LLMOps for GenAI
Flagship work
Products and applied ML systems, shown through live interfaces and published technical work.
Eco Route
2026
Outcome:Built a map-first planner with a selectable time–fuel graph, foreground driving guidance, multiple stops, return trips, and saved cars. Fuel predictions remain uncalibrated estimates.
An early-beta Android route planner that compares extra travel time with estimated fuel and cost savings on an interactive graph, with calculations running on your phone.
- Kotlin
- Jetpack Compose
- Route Optimization
- OpenStreetMap
Aligner Tracker
2026
Outcome:Delivered a local-first phone app with one-tap IN/OUT tracking, timezone-aware daily accounting, encrypted portable backups, reminders, reports, and private progress photos.
A free, open-source Android app for recording clear-aligner wear, following a user-entered tray schedule, and keeping private progress records offline.
- Kotlin
- Jetpack Compose
- Room
- WorkManager
Timeo
2025
Outcome:Pilot users reduced schedule planning from about 3 hours to around 20 minutes.
Scheduling SaaS for independent restaurants and cafés: bring availability and coverage together, generate a draft, and review it before sharing.
- Optimization
- Product
- Operations AI
Outcome:A hybrid HGFD + XGBoost model improved precision by 17.4% over the XGBoost baseline in a business-unit study.
Heterogeneous graph neural network pipeline over claims, customers, and provider relationships.
- Graph Neural Networks
- PyTorch Geometric
- Insurance ML
Spiaggia Oggi
2026
Outcome:Published 1,128 named destinations across 15 coastal regions while keeping missing information and source limitations explicit.
Nationwide Italian beach discovery guide for finding and comparing named destinations with visible source provenance.
- Next.js
- PostgreSQL
- Geospatial Data
Outcome:Published both semesters from 2016 through 2025 with progressive map detail, compact search, historical comparisons, and shareable views.
Nationwide map for exploring official residential OMI sale quotations across Italy by area, property type, and semester.
- Next.js
- MapLibre
- PostGIS
- Geospatial Data
Timeline
2025 – present
Full-Stack AI Engineer
NLB d.d., Ljubljana (opens in new tab)
- Led a student team building an agentic AI system with orchestration and validation checkpoints for internal banking workflows.
- Shipped a GenAI feature with web search, retrieval-augmented generation, and image generation.
- Built dynamic graph neural networks for monitoring in banking workflows.
2025 – present
Founder
Timeo (timeo.matejkalc.com) (opens in new tab)
- Built and launched Timeo, a scheduling SaaS for independent restaurants and cafés.
- For pilot users, schedule preparation dropped from about 3 hours to around 20 minutes.
2024 – 2025
Data Scientist
Zurich Insurance Group, Ljubljana (opens in new tab)
- Developed graph ML for automobile fraud detection; a hybrid model improved precision by 17.4% over the XGBoost baseline in a business-unit study.
- Developed Databricks workflows that reduced batch inference time by 75%.
2023 – 2024
Data Scientist (Student)
Medius.si d.o.o., Ljubljana (opens in new tab)
- Created a PyTorch package for one-day-ahead solar power production forecasting with recurrent neural networks.
More work
Earlier products and applied machine-learning projects spanning geospatial data, forecasting, and large-scale modeling.
Outcome:Built an open-source spatiotemporal GNN implementation and technical report as part of a four-person team.
Sensor-graph forecasting model for highway traffic prediction several hours ahead.
- Temporal GNN
- Time Series
- Spatial Data
Outcome:Built and tuned multiple model families with Bayesian optimization on HPC resources.
Compared neural and factorization models for click-through-rate prediction on Outbrain data.
- CTR Modeling
- Deep Learning
- Bayesian Tuning
About
I build end-to-end AI products for production use, from orchestration and evaluation on the backend to usable frontend experiences. In regulated environments, I prioritize observability and reliability. In products, I focus on user value and iteration speed.
- Core stack
- TypeScript · Next.js · Python · FastAPI · PostgreSQL
- Modeling
- RAG · Agent Orchestration · LangGraph Workflows · LLM Evaluation · Tool-Using AI Systems
Education
- MSc in Data Science, Faculty of Computer and Information Science, University of Ljubljana (GPA 9.0)
- BSc in Computer Science, Faculty of Computer and Information Science, University of Ljubljana (GPA 9.1)
Achievements
- 1st place — IEDC Case Study Competition (NLB team, advancing to international round) (opens in new tab)
- 1st place — Data Science Hackathon (Etrel, EV charging clustering)
- 1st place — NLP word sense disambiguation with SloBERTa (opens in new tab)
- 3rd place — Data Science Project Competition (2021 and 2022) (opens in new tab)
Let’s talk
I’m open to selected AI engineering roles and product collaborations where reliable systems, measurable outcomes, and thoughtful delivery matter.