Yashwantej Dyavari Shetty
Data Engineer Data Scientist @PNC
Signup · Get unlimited contacts
WORK HISTORY
Data Engineer Data Scientist @PNC
Cleveland, OH, US
Designed LLM powered workflows using Python, LangChain, and OpenAI APIs to automate internal knowledge retrieval and generate structured insights from enterprise datasets.Built retrieval augmented generation pipelines using vector embeddings and semantic search to enable contextual AI responses across internal documentation and knowledge bases.Developed prompt engineering frameworks using structured prompts, few shot examples, and prompt chaining to produce reliable AI generated outputs for analytics and reporting workflows.Implemented prompt evaluation frameworks including scoring rubrics, benchmark datasets, and regression testing to measure output quality and detect drift.Designed AI guardrails including validation checks, output filtering, and prompt injection protections ensuring secure and compliant AI system usage.Built automated pipelines using Python and Spark to ingest enterprise documents and transform them into searchable knowledge repositories used by AI assistants.Developed prompt libraries and reusable prompt templates enabling consistent AI outputs across multiple enterprise workflows.Designed and implemented scalable cloud based data pipelines using Python, SQL, and Spark to ingest and process large enterprise financial datasets.Built distributed ELT workflows integrating multiple enterprise systems including APIs, relational databases, and flat file data sources.Developed transformation pipelines converting raw JSON, XML, and relational datasets into structured analytics ready data models.Implemented REST based API integrations and JDBC connectivity frameworks to ingest enterprise data from external and internal systems.Engineered cloud based data warehouse solutions using Snowflake and Redshift supporting large scale enterprise analytics workloads.Developed automated data cleansing, standardization, and validation frameworks improving reliability of enterprise data pipelines.
EDUCATION
Indira Gandhi National Open University
Master of Public Administration - MPA, Public Administration
University of Memphis
Master of Science - MS, Data Science
Jawaharlal Nehru Technological University
Bachelor of Science - BS, Computer Science and Engineering
ABOUT YASHWANTEJ DYAVARI SHETTY
Senior Data Engineer / Scientist with 6 years of experience designing and operating scalable ETL and ELT pipelines, building reliable cloud data platforms, and optimizing enterprise data warehouses using Python, SQL, Spark, and distributed processing frameworksStrong expertise developing data engineering solutions across AWS, Azure, Databricks, Snowflake, and BigQuery environments supporting enterprise analytics and machine learning workflowsExtensive experience designing high availability data pipelines that ingest, transform, and process large healthcare datasets across distributed computing platforms.Hands on experience building PySpark based ingestion pipelines in Databricks processing large scale claims and eligibility datasets stored in formats including Parquet, CSV, and JSON.Proven ability to design and optimize enterprise data warehouses using Snowflake SQL and advanced query optimization techniques supporting large scale analytics initiativeStrong expertise working with big data technologies including Apache Spark, Spark SQL, Hive, and Hadoop for distributed data processing and analytics.Strong expertise in Python and SQL for building AI enabled pipelines, automation tools, and data systems supporting analytics and intelligent applications.Proficient in designing prompt engineering frameworks including structured prompting, few shot prompting, prompt chaining, and tool use prompting for reliable LLM workflows.Hands on experience building retrieval augmented generation pipelines using embeddings, vector search, and document chunking to enable contextual AI assistance.Strong experience implementing API based data integrations using REST, SOAP, HTTP webhooks, and JDBC or ODBC connectivity for enterprise systems.Hands on experience implementing monitoring, alerting, and logging frameworks ensuring reliability and traceability of enterprise data pipelinesSkilled in applying data governance practices including metadata management, data dictionaries, and standardized enterprise data definitionsExperienced collaborating with analytics, compliance, and engineering teams ensuring data transformations align with healthcare regulatory requirements including HIPAA and NCQA reporting standards.Experienced working in Agile development environments using version control, CI CD frameworks, and collaborative engineering practices to deliver reliable data platformsBuilt automated AI workflows that transform internal knowledge bases and operational data into insights
This profile is compiled from publicly available professional sources. Unifers is not affiliated with or endorsed by LinkedIn. Request removal of this profile.