Applied Data Scientist | Published Researcher | AI Application Developer
Passionate about bridging cutting-edge AI research with practical solutions that enhance human wellbeing and create meaningful impact.
As an applied data scientist, I'm passionate about translating complex ML/NLP concepts into practical solutions that make a real difference in people's lives.
I believe AI should enhance human potential rather than replace it. This philosophy guides everything I build - from optimizing ML pipelines for real-world deployment to developing AI applications focused on human wellbeing.
Inspired by the next generation, I'm committed to building technology that creates a better future for our children and families.
Co-authored with Ofir Tal
Demonstrated the power of AI in interdisciplinary applications by applying machine learning techniques to optimize biological marker detection, showcasing how AI can enhance scientific instrumentation and measurement accuracy.
View PublicationI believe in bridging the gap between academic research and practical implementation. My work focuses on making cutting-edge AI techniques accessible and applicable to real-world challenges.
Sharing practical insights on the behaviour of LLMs in the presence of context, focusing on factuality and truthfulness.
Read MoreSharing practical insights on evaluating RAG systems in production environments, focusing on factuality and truthfulness.
Read MoreA comprehensive resource for understanding the intricacies of LLM training, from foundational concepts to advanced implementation strategies.
Read MoreSharing my personal journey of building an AI-powered personal development assistant, from initial concept to production deployment.
Read MoreBuilding an AI assistant focused on human wellbeing and personal growth. Exploring innovative applications of NLP for helping people maintain balance and achieve their goals through intelligent, personalized guidance.
Read MoreA comprehensive multi-model AI comparison platform for evaluating responses from Gemini 2.5 Pro and Ollama models. Features dual-mode querying, custom evaluation prompts, GPU memory management, and response history tracking.
Machine learning pipeline for predicting phytoplankton biomass in Lake Kinneret using fluoroprobe sensor data. Features advanced data preprocessing, multi-model comparison (XGBoost, Random Forest, SVM), and comprehensive evaluation metrics. This interdisciplinary project demonstrates the power of AI in environmental science applications.
Passionate about bridging cutting-edge research with practical applications. Interested in collaboration or learning more about these projects?
Always interested in connecting with fellow builders, researchers, and anyone passionate about responsible AI development.