AI/ML | Data Science | MLOps | Cloud Analytics
I build portfolio-grade AI, machine learning, and data science systems that demonstrate end-to-end delivery: data ingestion, feature engineering, model training, evaluation, deployment, monitoring, governance, and cloud architecture.
My work focuses on practical AI/ML engineering across Azure, AWS, and GCP, with emphasis on production-style workflows, responsible AI, MLOps, RAG/LLMOps, healthcare analytics, risk intelligence, and operational decision support.
- Machine Learning & Data Science: classification, regression, anomaly detection, forecasting, experimentation, model evaluation, and risk scoring
- MLOps & AI Engineering: CI/CD, model monitoring, drift detection, batch/real-time inference, governance, and reproducible pipelines
- GenAI & RAG Systems: document ingestion, retrieval, grounded generation, guardrails, evaluation, and LLMOps workflows
- Cloud Platforms: Azure, AWS, and GCP applied to AI/ML, analytics, security, and data engineering use cases
- Healthcare & Operational Analytics: patient flow, readmission risk, long-stayer risk, ambulance handover delays, bed allocation, and pathway intelligence
Production-style streaming ML system for event ingestion, feature processing, live inference, anomaly detection, alerting, monitoring, and drift evaluation.
AI governance platform covering model inventory, policy checks, risk scoring, access review, audit evidence, cost monitoring, and model monitoring.
RAG and LLMOps platform with document ingestion, mock embeddings, vector retrieval, grounded generation, guardrails, evaluation, and monitoring.
ML platform for fraud detection, churn prediction, anomaly detection, experimentation, monitoring, and risk inference.
Microsoft 365 / Entra ID posture monitoring project using Graph API foundations, IAM checks, risk scoring, compliance mapping, and executive reporting.
Enterprise-grade Databricks Lakehouse architecture covering batch processing, streaming, MLflow, LLM/RAG, governance, and CI/CD.
Languages: Python, SQL
ML/AI: scikit-learn, XGBoost, MLflow, model evaluation, drift monitoring, RAG/LLMOps concepts
Data Engineering: batch pipelines, streaming concepts, feature pipelines, data validation
Cloud: Azure, AWS, GCP
DevOps/MLOps: GitHub Actions, CI/CD, Docker, testing, reproducible project structure
BI & Analytics: Power BI, Tableau, operational dashboards
I am building a focused AI/ML/Data Science portfolio that demonstrates:
- end-to-end ML systems
- production-style deployment patterns
- responsible AI and model governance
- healthcare and operational analytics
- cloud-native AI/ML architecture
- clean, well-documented repositories