Hello! I am an AI/ML Engineer focused on building applied AI systems using LLM applications, RAG pipelines, agentic workflows, ML APIs, FastAPI services, Docker-based deployment, CI/CD, model evaluation, monitoring, and MLOps practices. My hands-on engineering work includes AI/ML systems for decision intelligence, fraud detection, recommender systems, customer conversion prediction, and biomedical QA. These projects combine Python, FastAPI, scikit-learn, XGBoost, LightGBM, CatBoost, PyTorch, TensorFlow/Keras, Hugging Face, OpenAI API, LangChain/LangGraph-style workflows, vector search, Docker, GitHub Actions, AWS, Azure, and responsible AI documentation. I build AI systems with a production-oriented mindset: problem understanding, data validation, baseline modelling, ML/LLM workflow design, API integration, evaluation, testing, containerization, CI/CD, monitoring, rollback planning, and continuous improvement. My strongest project areas include: • Agentic AI + RAG decision-support systems • Fraud detection ML systems with FastAPI model serving • Production-ready ML APIs with Docker and CI/CD • Recommender systems and multimodal product similarity • Biomedical QA LLM fine-tuning workflows • MLOps, model evaluation, monitoring, and deployment-ready architecture Before focusing on AI engineering, I worked in data analytics and business intelligence, using Python, SQL, Power BI, Excel, KPI reporting, and stakeholder-facing decision support across sales, operations, and finance. This background helps me understand real business data, operational workflows, and decision-making problems when building AI/ML systems.…Hello! I am an AI/ML Engineer focused on building applied AI systems using LLM applications, RAG pipelines, agentic workflows, ML APIs, FastAPI services, Docker-based deployment, CI/CD, model evaluation, monitoring, and MLOps practices. My hands-on engineering work includes AI/ML systems for decision intelligence, fraud detection, recommender systems, customer conversion prediction, and biomedical QA. These projects combine Python, FastAPI, scikit-learn, XGBoost, LightGBM, CatBoost, PyTorch, TensorFlow/Keras, Hugging Face, OpenAI API, LangChain/LangGraph-style workflows, vector search, Docker, GitHub Actions, AWS, Azure, and responsible AI documentation. I build AI systems with a production-oriented mindset: problem understanding, data validation, baseline modelling, ML/LLM workflow design, API integration, evaluation, testing, containerization, CI/CD, monitoring, rollback planning, and continuous improvement. My strongest project areas include: • Agentic AI + RAG decision-support systems • Fraud detection ML systems with FastAPI model serving • Production-ready ML APIs with Docker and CI/CD • Recommender systems and multimodal product similarity • Biomedical QA LLM fine-tuning workflows • MLOps, model evaluation, monitoring, and deployment-ready architecture Before focusing on AI engineering, I worked in data analytics and business intelligence, using Python, SQL, Power BI, Excel, KPI reporting, and stakeholder-facing decision support across sales, operations, and finance. This background helps me understand real business data, operational workflows, and decision-making problems when building AI/ML systems.WWWW…