Looking for a job

Sandhya Goud

@sandhyagoud

Message

Applied Data Engineer at Morgan Stanley building financial RAG pipelines that improved retrieval relevance by 20–25%.

United States

Message

At Morgan Stanley, I build production data solutions that connect structured and unstructured financial information to search, analytics, and AI applications. My RAG pipelines improved retrieval relevance by approximately 20–25%, and evaluation frameworks helped reduce manual research effort by approximately 30%.

Previously, at Capgemini/ Synchrony, I engineered financial data pipelines and cloud analytics workflows, reducing data discrepancies by more than 30%. At Capgemini/ Citi Bank and TMF Group, I developed SQL pipelines, reporting workflows, and dashboards for banking and financial operations.

Experience

Work history, roles, and key accomplishments

Current

Applied Data Engineer

Current

Morgan Stanley

Mar 2025 - Present (1 year 7 months)

Designed and operated production data solutions using Python, SQL, Azure Blob Storage, and Azure AI Search, integrating structured and unstructured financial data. Built scalable batch ingestion and ETL pipelines supporting over 1M document chunks, and developed RAG pipelines using Azure OpenAI and LangChain.

Python SQL Azure Blob Storage Azure AI Search ETL Azure OpenAI Lang Chain LangGraph fastAPI Docker Jenkins CI CD RBAC Audit Logging Agile Scrum

Sr. Data Analyst / Engineer

Capgemini

Feb 2023 - Aug 2024 (1 year 6 months)

Engineered and maintained ETL pipelines using Ab Initio, Python, and SQL, processing millions of financial records weekly into an Oracle Data Warehouse. Developed parameterized Azure Data Factory pipelines and dbt models, and optimized batch processing to reduce time by 20-25%.

Ab Initio Python SQL Oracle Azure Data Factory Data Lake Storage Gen2 Snowflake DBT Azure Key Vault azure monitor Autosys Pandas Data Profiling Data Quality Agile Scrum

Data Analyst

Capgemini

Nov 2021 - Feb 2023 (1 year 3 months)

Developed and optimized SQL data pipelines delivering validated banking data to 10+ business-critical BI dashboards. Refactored long-running queries to reduce execution time by 20-30% and implemented automated data-quality checks.

SQL Azure Data Factory Azure Data Lake Storage Power BI Data Quality Root Cause Analysis Stored Procedures Query Optimization

Data Analyst

TMF Group

Jun 2020 - Nov 2021 (1 year 5 months)

Analyzed financial and operational records using SQL, Python, R, and Excel. Built scheduled ETL workflows and automated reports, reducing manual effort by approximately 30% and improving reporting accuracy.