Open to opportunities

Rupali Shisode

@rupalishisode

Message

I build enterprise RAG, ML, and data platforms on AWS.

India

Message

What I'm looking for

I'm looking to build secure, governed generative AI, RAG, and machine learning platforms that turn complex enterprise data into business-ready outcomes. I value cross-functional collaboration, scalable AWS engineering, and opportunities to lead AI solution architecture.

At Tata Consultancy Services, I architect enterprise RAG and agentic systems for Vanguard using Amazon Bedrock, LangGraph, LangChain, OpenSearch, and Chroma DB. My work improved retrieval accuracy by 35% through RAGAS-based evaluation and client-aligned frameworks.

Previously at Roche Information Solutions, I led integrated AWS data pipelines and machine learning deployments for NaCore, NaPathology, NaPoc, Navify Integrator, and PandiHub. I built AI-ready feature pipelines, production inference with SageMaker and Redshift ML, and MLOps workflows that reduced ETL processing load times by 35%.

I bring 8.9+ years of healthcare, life sciences, and enterprise data engineering experience, including clinical-data ETL at Saama Technologies and CMS-compliant reporting data ingestion at Figmd India. I focus on secure, governed AI solutions that turn fragmented data into reliable business outcomes.

Experience

Work history, roles, and key accomplishments

Current

Lead AI / Data Engineer

Current

Tata Consultancy Services

Feb 2026 - Present (6 months)

Architected and deployed enterprise RAG systems on Amazon Bedrock using LangGraph and LangChain, improving retrieval accuracy by 35%. Implemented MCP for secure LLM access to proprietary databases and accelerated prototyping by 30% with Claude Code and GitHub Copilot.

RAG Lang Chain LangGraph Model Context Protocol AWS PySpark SQL Python AWS Glue AWS Lambda Athena Sagemaker MLOps Gitlab Claude Code GitHub Co Pilot

AI Data Engineer

Roche Information Solutions

Dec 2020 - Feb 2026 (5 years 2 months)

Led end-to-end design and deployment of integrated data pipelines and ML models on AWS, including scalable feature engineering and production inference. Optimized Spark and AWS Glue ETL jobs, reducing processing load times by 35% and built MLOps pipelines with GitLab.

AWS AWS Glue PySpark Lambda S3 Athena Sagemaker ETL ELT MLOps Gitlab Python SQL Data Quality

Data Engineer

Saama Technologies

Nov 2019 - Dec 2020 (1 year 1 month)

Designed and developed ETL workflows using PostgreSQL and AWS Redshift for clinical trial datasets. Migrated and optimized data pipelines with SQL/SparkSQL query tuning and established proactive monitoring for high reliability.

PostgreSQL AWS RedShift ETL SQL SparkSQL Data Pipelines Monitoring

ETL + SQL Developer

Figmd India Pvt. Ltd.

Oct 2017 - Nov 2019 (2 years 1 month)

Ingested, transformed, and validated physician-level data for CMS-compliant reporting using SQL Server and Oracle. Automated data ingestion with Java-based utilities, improving turnaround time by 20%.

SQL Server Oracle ETL SQL Java Data Validation Automation