Skip to main content

Matej Kalc · Portfolio

Full-Stack AI Engineer building LLM products from prototype to production.

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
View projectsResumeContact

Flagship work

Products and applied ML systems, shown through live interfaces and published technical work.

Timeo demo showing an AI-assisted retail schedule being created from an uploaded employee file
Privacy-safe product demo

Timeo (SaaS) - Scheduling in seconds

2025

Optimization-based scheduling platform that builds compliant schedules in seconds.

Outcome

Pilot users reduced schedule planning from about 3 hours to around 20 minutes.

  • Optimization
  • Product
  • Operations AI
View Timeo project detailsTry the Timeo product (opens in new tab)
Architecture diagram from the thesis showing heterogeneous graph layers followed by linear prediction layers
Architecture from the published thesis

Automobile Insurance Fraud Detection

2024

Heterogeneous graph neural network pipeline over claims, customers, and provider relationships.

Outcome

Improved precision by 17.4% over the XGBoost baseline in the published evaluation.

  • Graph Neural Networks
  • PyTorch Geometric
  • Insurance ML
View fraud-detection project detailsRead the fraud-detection thesis (opens in new tab)
Spiaggia Oggi discovery page showing provenance filters and named Italian beach destinations
Live public beach explorer

Spiaggia Oggi

2026

Nationwide Italian beach discovery guide for finding and comparing named destinations with visible source provenance.

Outcome

Published 1,128 named destinations across 15 coastal regions while keeping missing information and source limitations explicit.

  • Next.js
  • PostgreSQL
  • Geospatial Data
View Spiaggia Oggi project detailsExplore Spiaggia Oggi (opens in new tab)

Timeline

  1. 2025 - present

    Full-Stack AI Engineer

    NLB d.d., Ljubljana (opens in new tab)

    • Led a student team building an agentic document-validation system with orchestration and validation checkpoints, estimated to reduce manual work by 1,000+ hours per year.
    • Shipped an AI report generator with web search, retrieval-augmented generation, and image generation.
    • Built dynamic graph neural networks for anti-money-laundering monitoring in banking workflows.

  2. 2025 - present

    Founder

    Timeo (timeo.matejkalc.com) (opens in new tab)

    • Built and launched Timeo, a scheduling SaaS for small businesses.
    • For pilot users, schedule preparation dropped from about 3 hours to around 20 minutes.

  3. 2024 - 2025

    Data Scientist

    Zurich Insurance Group, Ljubljana (opens in new tab)

    • Introduced graph neural networks for automobile insurance fraud detection, improving precision by 17.4% over the XGBoost baseline in the published evaluation.
    • Developed Databricks workflows that reduced batch inference time by 75%.

  4. 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.

Valori Immobiliari Trieste

2026

Interactive map of Trieste real-estate values with OMI zone ranges and local market filters.

Outcome

Turned public valuation data into a clearer browsing experience for exploring price differences across the city.

  • Next.js
  • Interactive Maps
  • Real Estate Data
View the Trieste property-map detailsExplore Valori Immobiliari Trieste (opens in new tab)

Traffic Prediction with Temporal GNNs

2023

Sensor-graph forecasting model for highway traffic prediction several hours ahead.

Outcome

Built an open-source spatiotemporal GNN implementation and technical report as part of a four-person team.

  • Temporal GNN
  • Time Series
  • Spatial Data
View traffic-prediction project detailsView the traffic-prediction repository (opens in new tab)

CTR Prediction at Scale

2022

Compared neural and factorization models for click-through-rate prediction on Outbrain data.

Outcome

Built and tuned multiple model families with Bayesian optimization on HPC resources.

  • CTR Modeling
  • Deep Learning
  • Bayesian Tuning
View CTR-prediction project detailsRead the CTR-prediction thesis (opens in new tab)

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

Achievements

Let’s talk

I’m open to selected AI engineering roles and product collaborations where reliable systems, measurable outcomes, and thoughtful delivery matter.

matejkalc99@protonmail.com

Trieste, Italy