I am an AI Engineer with 4+ years of experience building and deploying machine learning, Generative AI, and LLM-powered applications across enterprise environments. My work combines applied AI, software engineering, data engineering, and MLOps, with a strong focus on building scalable and reliable production systems. My recent experience includes Generative AI applications, Retrieval-Augmented Generation (RAG), semantic search, vector retrieval, AI agents, NLP systems, predictive modeling, and ML inference services. I have worked with Azure OpenAI, OpenAI APIs, LangChain, LangGraph, LlamaIndex, Hugging Face Transformers, PyTorch, TensorFlow, Scikit-learn, and FastAPI. At JPMorgan Chase, I have worked on enterprise LLM and RAG applications for document analysis and knowledge retrieval, integrating embeddings, vector databases, semantic search, enterprise data sources, and model inference. I have also developed FastAPI-based AI microservices, containerized services using Docker, deployed workloads through Kubernetes, and implemented MLflow-based experiment tracking, model versioning, CI/CD, and model deployment workflows. My work has also included evaluating retrieval quality, groundedness, response accuracy, hallucinations, and output validation to improve the reliability of AI systems. My background includes traditional machine learning and NLP, including classification, regression, predictive analytics, document classification, sentiment analysis, and information extraction. I have built preprocessing and feature engineering pipelines using Python, SQL, Pandas, Spark, and PySpark and worked with large-scale structured and unstructured datasets. I also have experience with PostgreSQL, MySQL, MongoDB, Redis, Pinecone, FAISS, ChromaDB, Apache Kafka, Apache Airflow, Docker, Kubernetes, AWS, Azure, and Google Cloud. My project work includes an Enterprise AI Knowledge Assistant using RAG and LangGraph-based agents for document summarization, question answering, and workflow orchestration, as well as an AI-powered customer support platform for ticket classification, intent detection, recommendations, and automated response generation. I am particularly interested in Applied AI Engineer, AI Engineer, Generative AI Engineer, LLM Engineer, and Machine Learning Engineer roles where I can build AI products end to end and take systems from experimentation to reliable production.…I am an AI Engineer with 4+ years of experience building and deploying machine learning, Generative AI, and LLM-powered applications across enterprise environments. My work combines applied AI, software engineering, data engineering, and MLOps, with a strong focus on building scalable and reliable production systems. My recent experience includes Generative AI applications, Retrieval-Augmented Generation (RAG), semantic search, vector retrieval, AI agents, NLP systems, predictive modeling, and ML inference services. I have worked with Azure OpenAI, OpenAI APIs, LangChain, LangGraph, LlamaIndex, Hugging Face Transformers, PyTorch, TensorFlow, Scikit-learn, and FastAPI. At JPMorgan Chase, I have worked on enterprise LLM and RAG applications for document analysis and knowledge retrieval, integrating embeddings, vector databases, semantic search, enterprise data sources, and model inference. I have also developed FastAPI-based AI microservices, containerized services using Docker, deployed workloads through Kubernetes, and implemented MLflow-based experiment tracking, model versioning, CI/CD, and model deployment workflows. My work has also included evaluating retrieval quality, groundedness, response accuracy, hallucinations, and output validation to improve the reliability of AI systems. My background includes traditional machine learning and NLP, including classification, regression, predictive analytics, document classification, sentiment analysis, and information extraction. I have built preprocessing and feature engineering pipelines using Python, SQL, Pandas, Spark, and PySpark and worked with large-scale structured and unstructured datasets. I also have experience with PostgreSQL, MySQL, MongoDB, Redis, Pinecone, FAISS, ChromaDB, Apache Kafka, Apache Airflow, Docker, Kubernetes, AWS, Azure, and Google Cloud. My project work includes an Enterprise AI Knowledge Assistant using RAG and LangGraph-based agents for document summarization, question answering, and workflow orchestration, as well as an AI-powered customer support platform for ticket classification, intent detection, recommendations, and automated response generation. I am particularly interested in Applied AI Engineer, AI Engineer, Generative AI Engineer, LLM Engineer, and Machine Learning Engineer roles where I can build AI products end to end and take systems from experimentation to reliable production.WWWW…