I am a Data Scientist and AI/ML Engineer with a strong foundation in retail analytics, pricing strategy, and customer experience platforms.
I recently completed my MSc in Data Science (June 2025, AUEB) and I am now pursuing my career goal of becoming a Lead Data Scientist, while building advanced AI engineering skills to deliver scalable, production-ready AI systems.

💡 My profile combines:

• Strategic Data Science → interpretable ML models, feature engineering, applied research
• AI Engineering → deployment pipelines, MLOps, containerization, AI agents for real-world use
• Domain Expertise → retail, pricing, customer personalization, CX platforms

• Leading projects in recommender systems, forecasting, and personalization for retail and CX
• Building AI agents with LangChain, Flowise, and Supabase
• Developing MLOps pipelines for CI/CD, Docker/Kubernetes deployment, and Triton inference serving
• Bridging data science insights with enterprise AI systems

My long-term aspiration is to grow into a Lead Data Scientist, driving AI-first product development and team leadership,
while maintaining strong AI engineering expertise to ensure models move seamlessly from research into production.

• 📊 Retail Footfall Forecasting – Demand prediction from sensor data (Xovis)
• 🧾 Pricing Optimization in Retail – Advanced EDA & ML for price elasticity and promotion analysis
• 🤖 Multimodal Sentiment Classifier – BERT + Inception-v3 for social media content classification
• 🔗 Airbnb Graph Analysis – Neo4j & graph algorithms for community detection and link prediction
• 🎯 Recommender Systems (Clothing Domain) – Context-aware retrieval models using TensorFlow Recommenders
• 🩻 MURA Medical Imaging – CNN and Transfer Learning for abnormality detection

(🔗 Replace # with your actual repo links once published.)

• Deep Learning: MURA dataset (CNN, Transfer Learning, EfficientNetB0)
• Recommender Systems: Synthetic dataset (10k users, 1k items, TFR models)
• Data Mining: Neo4j Airbnb graph queries & clustering
• Optimization: Linear & Combinatorial Optimization (Python/CPLEX)
• Data Challenge: Kaggle-style competition (6th place with multimodal LR model)

• Languages: Python, R, SQL
• ML/DL: TensorFlow, PyTorch, Scikit-learn, Hugging Face Transformers
• EDA & Feature Engineering: Pandas, NumPy, Seaborn, Matplotlib, Plotly
• Databases: PostgreSQL, MySQL, MS SQL Server, MongoDB, Oracle
• Deployment & MLOps: Docker, FastAPI, CI/CD pipelines
• Systems: Linux (advanced), Windows Server

• Apache Spark, Hadoop
• Tableau, Power BI
• Kubernetes, Azure, AWS

• AI Agents (LangChain, Flowise, Triton Inference Server)
• Advanced MLOps orchestration

📧 Email: jasproudis@gmail.com