Pavan Krishna VUNNAM

AI Data Engineer with 3+ years of experience designing, implementing, and optimizing enterprise-scale data processing systems and AI-powered cloud architectures across AWS and Azure ecosystems. Proven expertise in building scalable ETL and ELT pipelines using AWS Glue, Lambda, Step Functions, Azure Data Factory, and Databricks. Specialized in Retrieval-Augmented Generation (RAG), semantic search architectures, embeddings pipelines, and LLM integration using Amazon Bedrock, Kendra, and OpenSearch. Experienced in architecting AI-ready data lakes with partitioning, encryption, lifecycle management, and metadata governance. Strong background in distributed data processing using PySpark for large-scale transformations and feature engineering. Hands-on experience implementing Attribute-Based Access Control (ABAC) using IAM policies and S3 object tagging for ITAR and EAR compliance. Proficient in Python, SQL, and API integrations for automation, transformation, and data orchestration. Experienced in processing large volumes of structured and unstructured files including PDF, CSV, DAT, TXT, and image-based documents. Skilled in cross-cloud architecture integrating AWS and Azure platforms for unified analytics and machine learning workflows. Strong knowledge of observability, logging, audit trails, and monitoring using CloudWatch and structured tagging frameworks. Proven ability to reduce operational overhead through automation, performance optimization, and dashboard engineering. Passionate about building secure, scalable, AI-driven data ecosystems that align engineering excellence with business impact.