S

Sowmya Yalavarthi

About

Detail

Virginia, United States

Timeline


work
Job
school
Education

Résumé


Jobs verified_user 0% verified
  • Broadridge
    GenAI Engineer
    Broadridge
    Jan 2024 - Current (2 years 5 months)
    Currently working on a production Generative AI initiative focused on financial document intelligence, enabling secure, accurate, and context-aware access to enterprise financial and compliance documents. Designed and implemented Retrieval-Augmented Generation (RAG) pipelines using Azure Cognitive Search (hybrid keyword + vector search) and LangChain, enabling reliable semantic search and natural- language Q&A over large volumes of PDFs and structured data. Implemented vector similarity search workflows by storing embeddings in an Azure Vector Store, improving retrieval accuracy and response relevance for downstream GenAI applications. Built end-to-end document ingestion pipelines using Azure Data Factory, Databricks, Python, and PySpark, h
  • Fifth Third Bank
    Gen AI | Data Scientist
    Fifth Third Bank
    Aug 2021 - Dec 2023 (2 years 5 months)
    Built a serverless RAG stack on AWS (API Gateway, Lambda, S3-KMS, OpenSearch BM25 + FAISS semantic) using hierarchical document chunking at indexing and semantic compression at query time, resulting in 18% higher retrieval precision, 22% fewer tokens per request, and 53% lower p95 latency. Implemented function calling with LangChain tools and Amazon Bedrock (Agents) to invoke internal APIs and market-data sources in real time, resulting in fewer stale-data errors and reduced manual integration overhead. Designed prompt routing, caching, and retry/backoff in AWS Lambda, resulting in a 20% reduction in LLM API spend while maintaining response quality under load. Fine-tuned and quantified domain transformers on SageMaker using PEFT (LoRA/QLORA
  • Ensemble Health Partners
    Data Scientist | AIML Engineer
    Ensemble Health Partners
    Nov 2019 - Aug 2021 (1 year 10 months)
    Worked on data science and applied machine learning solutions to support healthcare revenue cycle management, focusing on payment variance analysis, denial patterns, and operational optimization. Performed exploratory data analysis (EDA) on large healthcare datasets including claims, billing, payment, and adjustment records to identify trends, anomalies, and drivers of revenue leakage. Built and evaluated predictive and classification models using Python and SQL to support use cases such as denial risk identification, underpayment detection, and prioritization of follow-up actions. Engineered domain-specific features from structured healthcare data, including transaction histories, payer behavior patterns, and time-based metrics, improving
  • AT&T
    Data Scientist | Big Data Engineer
    AT&T
    Jan 2018 - Nov 2019 (1 year 11 months)
    Designed Worked on large-scale enterprise data platforms supporting telecom operations, customer analytics, and reporting across multiple business units. Built and maintained ETL pipelines to ingest, transform, and load high-volume structured data from transactional systems into centralized data stores for analytics and reporting. Developed data transformation and aggregation logic using SQL and Python, enabling consistent, analysis-ready datasets for downstream reporting and analytical use cases. Performed data profiling, validation, and quality checks to ensure accuracy, completeness, and reliability of business-critical datasets. Supported operational and analytical reporting by preparing curated datasets and metrics used by business and
  • Tata Consultancy Services
    Data Engineer/Scientist
    Tata Consultancy Services
    Oct 2015 - Jun 2017 (1 year 9 months)
    Mainly engaged in data migration processes utilizing Cloudera, integrated with Bitbucket repository and TeamCity CICD. Replicated existing application logic and functionalities within Azure Data Lake, Data Factory, SQL Database, and SQL Data Warehouse environments. Proficient in Azure Cloud Services spanning PaaS & IaaS, including Azure Synapse Analytics, SQL, Azure Data Factory, Azure Analysis Services, Application Insights, Azure Monitoring, Key Vault, and Azure Data Lake. Managed Git repositories on Bitbucket, enforcing best practices for branch management, code review, and merge strategies to maintain code quality and project integrity. Conducted workload migrations from on-premises systems to Microsoft Azure Leveraging Azure Site Recov
Education verified_user 0% verified
  • KL University
    Bachelor's in ECE
    KL University
    Jan 2016
    India