Retrieval-Augmented Generation (RAG), Api, Python, Microservices, LangGraph, Langchain, Agentic AI, LLMs, multi-agent workflows, backend services, orchestration pipelines

Neo4j, Python, embeddings, AgentCore, AWS Bedrock, knowledge graphs, re-ranking, chunking strategy, prompt-library version-management, Veeva Vault, prompt engineering, RAG engineering, LangGraph, vector stores, VQL, Vault REST API, grounding

Gcp, Docker, Rest Apis, Azure, Python, AWS, LLMs, LangChain, RAG architecture, vector databases, Agentic AI, microservices architecture, LlamaIndex

Python, Gen AI, Langchain, ML algorithm, Llm

Tensorflow, Pytorch, Keras, Python, Statistical Analysis, image processing algorithms, machine learning pipelines

Machine Learning (ML), Artificial Intelligence (AI), Hadoop, Pyspark, Autosys, Sql, Angular, React, Spark, Python, Data Architecture, Metadata Management, DevOps practices, Flink, Copilot AI tool, Distributed data processing, Model context, Platform modernization, Performance optimization, Production support models, CI/CD pipelines, Agentic frameworks and flows, Enterprise controls, Data quality frameworks, Generative AI models, Protocol MCP

Pyspark, Apache Spark, Data Warehousing, Kafka, Dimensional Modeling, Sql, ELT, Apache Airflow, Git, Gcp, Terraform, Docker, Databricks, Azure, Python, Kubernetes, AWS, Etl, Apache Iceberg, Generative AI, Delta Lake, Apache Hudi, Large Language Models

event-driven architectures (Kafka or similar, cloud-native experience (GCP, Spring Boot, Microservices, concurrency, Reactjs, Performance Tuning, Rest Apis, Python, Azure, Java ecosystem, LLM-driven capabilities, Micro Frontends, GenAI architecture patterns, Embeddings and vector databases, RAG architectures, Agent frameworks and orchestration