Ml, Cloud Migration, Software Engineering, multi-agent systems, Generative AI, application transformation, LLMs, Ai, AI-assisted application modernization, Security, Agentic AI, platform upgrades, responsible AI practices, Governance, observability, RAG architectures, autonomous agents

Data Architecture for AI ML, Agent Core, Claude LLM Integration, RAG Retrieval-Augmented Generation, AI ML Workload Optimization, Amazon Bedrock, AWS SageMaker

Sql, Microsoft 365, Tableau, Pandas, Power Bi, Power Automate, Git, Flask, Github, Numpy, FastAPI, Python, Azure, Pytest, Docker, Claude, OpenAI, LlamaIndex, Google, Gemini, n8n, LangChain, Anthropic GPT, Pinecone, LangGraph, Zapier, Power Apps, Microsoft Copilot Studio, Sharepoint, Azure AI Search, requests, Dataverse, FAISS

Python, Knn, Neural Networks, SAS, Aws Cloud, Hadoop, Coding, Clustering, Hive, Tensorflow, Random Forest, Scala, Spark, Simulation, anomaly detection, Statistical methods, HDFS, Boosting Trees, Machine learning techniques, scenario analysis, GLM Regression, Teradata

Python, API design, Orchestration, tool calling, planning, explainability requirements, output parsing, parallel tool execution, stateful workflows, contextual compression, agent orchestration, query decomposition, context management, evaluation and testing frameworks for LLM-powered applications, search conversational AI, RAG patterns, multi-index routing, model governance, agentic architectures, cost token management, LLM capabilities and limitations, AWS cloud services, microservices architecture, prompt engineering, workflow automation, retrieval systems

data engineering , Technical Leadership, Pytorch, Pandas, Deep Learning, Numpy, MLops, Azure, python, langchain, model deployment, embeddings, production integration, model serving, model optimization, retrieval-augmented generation, vector search, data pipelines, langgraph, agentic ai, model evaluation, Mentoring, prompt engineering, pipeline architecture