Marjan Stoimchev · Computer Vision & ML Engineer

Marjan Stoimchev · Computer Vision & ML Engineer Skip to content Open to CV/ML Engineer · Applied Scientist · R&D Marjan Stoimchev Computer Vision & Machine Learning Engineer building production vision systems I'm an R&D engineer who turns research ideas into scalable, production-ready AI across computer vision, multimodal and vision-language models, and large-scale learning. I focus on two hard problems: getting strong results when labeled data is scarce, and making inference pipelines fast and robust enough to deploy. Ljubljana, Slovenia · Open to full-time roles · Remote or Relocation View Work Download Résumé Get in touch 7+ Years in AI R&D Research-to-production across computer vision, multimodal & ML systems PhD Computer Vision & Deep Learning R&D engineer bridging academic research and industry delivery Weeks→Min Faster, automated pipelines Self-supervised embedding workflows for clinical phenotyping at MedAI Label-efficient Less manual annotation Self-/semi-supervised learning and foundation-model adaptation Computer Vision / ML Engineering Consultant · Independent Consultancy Apr 2026 – Present Production segmentation and annotation systems for inventory image analysis. - Built an end-to-end segmentation-assisted annotation pipeline covering model training, inference integration, evaluation scripts, reproducible configs, and technical documentation. - Distilled a DINOv3-style teacher into a lightweight YOLOv9 student, transferring task-specific representations for fast proposal generation and annotation assistance. - Stood up a self-hosted CVAT environment and designed the full import → review → correct → export workflow around it. - Implemented active-learning triage that prioritizes images by confidence, entropy, and disagreement scoring so annotators spend time where it matters. - Engineered boundary-aware pseudo-mask refinement to cut mask leakage, holes, jagged edges, and under-segmentation, plus a synthetic image-mask generat