Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

Hi, I’m Ramya Chowdavaram, a Senior Data & AI Engineer with 9+ years of experience designing scalable data platforms and intelligent AI-driven systems. I specialize in building large-scale data pipelines, lakehouse architectures, and agentic AI applications leveraging LLMs, multi-agent workflows, RAG, and vector databases. I’ve delivered production-grade platforms using Python, Spark, Iceberg, Airflow, Azure ADLS, AKS, and Snowflake to empower enterprise analytics. I focus on reliable data infrastructure and AI-powered insights at scale.…Hi, I’m Ramya Chowdavaram, a Senior Data & AI Engineer with 9+ years of experience designing scalable data platforms and intelligent AI-driven systems. I specialize in building large-scale data pipelines, lakehouse architectures, and agentic AI applications leveraging LLMs, multi-agent workflows, RAG, and vector databases. I’ve delivered production-grade platforms using Python, Spark, Iceberg, Airflow, Azure ADLS, AKS, and Snowflake to empower enterprise analytics. I focus on reliable data infrastructure and AI-powered insights at scale.

Ramya Chowdavaram

Data Scientist, AI Engineer, Data Analyst, +2





Hi, I’m Ramya Chowdavaram, a Senior Data & AI Engineer with 9+ years of experience designing scalable data platforms and intelligent AI-driven systems. I specialize in building large-scale data pipelines, lakehouse architectures, and agentic AI applications leveraging LLMs, multi-agent workflows, RAG, and vector databases. I’ve delivered production-grade platforms using Python, Spark, Iceberg, Airflow, Azure ADLS, AKS, and Snowflake to empower enterprise analytics. I focus on reliable data infrastructure and AI-powered insights at scale.…Hi, I’m Ramya Chowdavaram, a Senior Data & AI Engineer with 9+ years of experience designing scalable data platforms and intelligent AI-driven systems. I specialize in building large-scale data pipelines, lakehouse architectures, and agentic AI applications leveraging LLMs, multi-agent workflows, RAG, and vector databases. I’ve delivered production-grade platforms using Python, Spark, Iceberg, Airflow, Azure ADLS, AKS, and Snowflake to empower enterprise analytics. I focus on reliable data infrastructure and AI-powered insights at scale.

Available to hire

Hi, I’m Ramya Chowdavaram, a Senior Data & AI Engineer with 9+ years of experience designing scalable data platforms and intelligent AI-driven systems. I specialize in building large-scale data pipelines, lakehouse architectures, and agentic AI applications leveraging LLMs, multi-agent workflows, RAG, and vector databases.

I’ve delivered production-grade platforms using Python, Spark, Iceberg, Airflow, Azure ADLS, AKS, and Snowflake to empower enterprise analytics. I focus on reliable data infrastructure and AI-powered insights at scale.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Language

English

Fluent

Work Experience

Senior Data Engineer at GEICO

July 1, 2023 - Present

Architected a production-grade Agentic AI framework with a central Supervisor Agent to orchestrate multi-agent workflows, integrating MCP tools to connect LLMs with enterprise data sources, reducing complex query resolution time by 35%. Designed and deployed a scalable Retrieval-Augmented Generation (RAG) platform using vector embeddings and Milvus for semantic search across pipeline docs, ingestion metadata, and operational logs; improved retrieval precision by 40%. Implemented agent memory and context management with vector embeddings and metadata-backed state stores for persistent conversational context and multi-turn reasoning. Enabled LLM tool-calling to dynamically invoke MCP tools for diagnostics and query execution. Built an enterprise Lakehouse platform on Azure ADLS, AKS, Spark, Iceberg, Airflow, and Snowflake; supported ingestion workloads processing 1.3B records/day. Led Kafka bifurcation project migrating pipelines to Spark/Airflow ingestion framework; 100% reliable ingest

Data Engineer at Wells Fargo

January 1, 2022 - July 1, 2023

Designed Spark-based data pipelines to ingest risk identification data from ServiceNow APIs into the Data Lake; published curated datasets to downstream consumers via Kafka. Migrated legacy SQL Server ETL workflows to PySpark, enabling scalable batch processing and improved reliability. Optimized Spark jobs with broadcast joins, repartitioning, and memory tuning; reduced execution times by 25% and improved throughput. Orchestrated end-to-end workflows using Apache Airflow with CI/CD deployments via Jenkins, ensuring production-grade reliability and maintainability of pipelines.

Software Engineer – Big Data Developer at Cognizant

October 1, 2011 - April 1, 2017

Designed and executed large-scale ETL migrations from Oracle and other RDBMS to Hadoop data lake using Sqoop, PySpark, Hive; built PySpark batch processing pipelines and optimized formats, achieving cost and performance gains. Implemented data modeling and optimization techniques including partitioning, bucketing, Snappy compression, and columnar formats (Parquet, Avro). Built reusable Python modules and Spark UDFs. Orchestrated complex workflows using Oozie and Autosys for reliable automated execution.