Alp Komban

About

Applied ML/LLM practitioner working in healthcare-facing products, using RAG and LoRA fine-tuning on medical data and implementing production monitoring (confidence scoring) for clinician oversight. Has hands-on experience debugging agentic/LLM pipelines (including OCR preprocessing fixes) and regularly delivers technical demos to doctors, investors, and conferences—contributing to adoption and even helping close a funding round through end-to-end pipeline walkthroughs.

Experience

Education

Key Strengths

• Took healthcare LLM/RAG prototype to production with LoRA fine-tuning
• Diagnosed and corrected model bias from skewed label distribution using weighted loss
• Production-minded monitoring using confidence scores to flag uncertainty for clinician oversight
• Systematic real-time debugging of LLM workflows via logs, fallbacks, and component-level tracing
• Improved OCR+LLM pipeline reliability by adding document orientation detection to prevent garbage inputs
• Strong technical communication—tailors demos for doctors/investors by emphasizing trust, citations, and end-to-end checks
• Helped close funding by presenting an end-to-end sensor regression pipeline with reliability checks