Home

harshitha - Cerfied GEN AI ENGINEER

[email protected]

Location: Charlotte, North Carolina, USA

Relocation:

Visa:

Resume file: Harshitha_Gen_ai_azure _Engineer (1)_1765380026531.docx Please check the file(s) for viruses. Files are checked manually and then made available for download.

SAI HARSHITHA PADALA [email protected] || +1-980-352-6677|| https://www.linkedin.com/in/psharshitha/ ________________________________________ PROFESSIONAL SUMMARY Data Scientist with 9+ years of experience designing and deploying AI and Generative AI solutions for large-scale healthcare workflows. Strong hands-on expertise in Python for model development, data processing, and end-to-end AI pipeline automation. Extensive experience building and optimizing deep-learning models using TensorFlow and PyTorch. Developed and customized LLM-based solutions for clinical summarization, document understanding, and healthcare analytics. Designed retrieval-augmented generation (RAG) pipelines integrating embeddings, vector search, and medical context retrieval. Worked with Azure AI services for hosting LLM inference, orchestrating workflows, and deploying ML components at scale. Built embedding pipelines using transformer encoders to support RAG, search, and retrieval-focused applications. Strong foundation in NLP covering text classification, summarization, semantic search, and transformer-based modeling. Applied fine-tuning and optimization strategies to improve model accuracy for healthcare-specific tasks. Experienced converting unstructured clinical and payer data into usable features for downstream ML and GenAI systems. Implemented evaluation strategies including model validation, grounding checks, and performance benchmarking. Supported healthcare decision-making by developing AI components that improved automation and reduced Manual review. Worked end-to-end across data ingestion, model development, deployment, monitoring, and continuous optimization on Azure. CERTIFICATIONS ________________________________________ Certified Oracle Cloud Infrastructure 2025 Certified Generative AI Professional LINK Coursera- Data Science Professional Certificate- IBM LINK TECHNICAL SKILLS Generative AI LLMs, Generative AI Pipelines, RAG (Retrieval-Augmented Generation), Fine-Tuning, Prompt Engineering, Model Guardrails, Structured Outputs Deep Learning & ML TensorFlow, PyTorch, Scikit-Learn, Neural Networks, Embeddings, Text Classification, Summarization, Transformer Models Azure AI Ecosystem Azure OpenAI, Azure Cognitive Search, Azure Functions, Azure Kubernetes Service (AKS), Azure Container Registry, Azure Storage, Azure SQL RAG & Retrieval Systems Embedding Generation, Vector Search, FAISS-style Indexing, Document Chunking, Context Augmentation, Retrieval Orchestration NLP Tokenization, Named Entity Extraction, Medical Text Processing, Semantic Search, Domain-Specific Text Cleaning Model Development & Optimization Model Training, Fine-Tuning, Evaluation Metrics, Hyperparameter Tuning, Drift Detection, Output Validation Python Engineering Python, FastAPI, Async Workflows, REST APIs, JSON/Parsers, Modular AI Components, Pipeline Automation Healthcare Data Claims Data, Clinical Documents, EHR/Provider Notes, HIPAA-Compliant Data Workflows Programming & Frameworks Python, FastAPI, Async I/O, PyTorch, TensorFlow, Scikit-Learn, REST APIs, JSON/Parsers Tools & Platforms Git, CI/CD, Jupyter, VS Code, Postman, MLflow (tracking), Application Insights PROFESSIONAL EXPERIENCE Client: Optum , Chicago, IL Role: Data Scientist-Gen AI Engineer Duration: October 2023 Present Project Scope: Designed and deployed enterprise-grade GenAI applications on Azure to support claims operations and internal teams. Built secure GPT-powered copilots, full RAG pipelines, and semantic search systems using Azure OpenAI, Cognitive Search, and App Services. Implemented cloud-native orchestration, CI/CD, and governance aligned with Optum s enterprise architecture standards. Designed end-to-end GenAI applications using Azure OpenAI (GPT-4, GPT-4o) integrated with App Services and serverless backend orchestration. Implemented production-grade RAG pipelines leveraging Azure Cognitive Search, vector semantic ranking, and metadata-driven retrieval. Built internal knowledge copilots for claims, provider rules, and operational SOPs using LangChain/LangGraph for routing and tool-calling workflows. Developed Python-based backend services for model orchestration, grounding, prompt routing, and document enrichment. Implemented semantic indexing across payer manuals, provider guides, and internal knowledge repositories using Cognitive Search skillsets. Built Azure Function based preprocessing pipelines for text extraction, parsing, chunking, and metadata tagging. Integrated Cognitive Search + Azure OpenAI to deliver accurate, explainable answers with grounding citations. Developed and maintained Azure DevOps CI/CD pipelines for automated build, deploy, environment promotion, and governance checks. Created monitoring dashboards and model telemetry using Application Insights and Azure Monitor. Deployed scalable GenAI inference workflows using Azure App Services and containerized Python services (Docker). Implemented secure access controls using Managed Identities, Key Vault, and enterprise policy enforcement. Designed structured output enforcement using Python validators and model guardrails. Collaborated cross-functionally with SMEs, developers, and enterprise architecture teams to define GenAI app patterns. Integrated Power BI dashboards to visualize GenAI interaction logs, grounding accuracy, and retrieval quality metrics. Troubleshot application performance, latency, and retrieval inconsistencies across Azure OpenAI and Cognitive Search. Environment: Azure OpenAI, Azure Cognitive Search, Azure App Services, Azure Functions, ADLS Gen2, Azure DevOps, Managed Identities, Key Vault, Docker, Python, FastAPI, LangChain, LangGraph, Power BI, Application Insights. Client: Spencer Health Solutions, Morrisville, NC Role: Data Scientist Duration: December 2021 July 2023 Project Scope: Built enterprise search and policy indexing pipelines on Azure to support payer operations. Developed Cognitive Search based semantic retrieval for benefits, authorization rules, and claims guidelines. In early 2023, created the first GenAI prototypes using Azure OpenAI for summarization, claims explanation, and policy Q&A, evolving into a light RAG-style workflow. Built Azure Data Lake ingestion pipelines for payer policies, benefit rules, and provider documentation Designed Cognitive Search indexes with enrichers for OCR, text extraction, metadata tagging, and semantic ranking. Implemented Python scripts for policy normalization, chunking, and structured metadata generation. Developed search APIs using Azure Functions and App Services for claims and policy lookup. Created Power BI datasets to surface payer rules and downstream insights for analytics teams. Built semantic search capabilities using Cognitive Search skillsets (2022). Introduced embedding-based retrieval when Azure OpenAI GA launched in early 2023. Developed GPT-3.5/GPT-4 prototypes for policy summarization, claims explanation, and user Q&A. Implemented early RAG-style retrieval by grounding model responses using Cognitive Search results (2023). Integrated prototype GenAI apps with backend Python services and Azure DevOps CI/CD pipelines. Collaborated with SMEs to validate policy grounding, hallucination control, and relevancy ranking. Produced architecture diagrams, data flows, and governance documentation for the GenAI POCs. Developed and optimized Azure App Services based microservices, ensuring scalable backend performance, request routing, and API reliability across environments. Designed cloud-native architectures using Azure Functions, Event Grid, ADLS Gen2, and App Services to support ingestion, indexing, and downstream application workflows. Implemented and managed Azure DevOps CI/CD pipelines, enabling automated unit testing, infrastructure deployment, release approvals, and environment promotion Collaborated with enterprise architecture, security, and governance teams to ensure all cloud components met Azure security baselines, compliance policies, RBAC standards, and audit requirements. Troubleshot and resolved production issues related to Azure networking, app configuration, storage access, and service dependencies, improving stability and reducing operational downtime. Environment:Azure Cognitive Search, Azure App Services, Azure Functions, ADLS Gen2, Azure DevOps, Python, FastAPI, Power BI, REST APIs, Git. Client: USCC Chicago , Illinois USA Role: Data Scientist -Machine Learning Engineer Duration: December 2019 November 2021 Project Scope: Developed machine learning and PySpark workflows to solve key telecom business problems predicting customer churn, improving retention strategies, and optimizing revenue across subscriber segments. Developed end-to-end churn forecasting pipelines using PySpark on AWS EMR, integrating daily subscriber activity, billing records, and call center interactions into ML-ready datasets. Built and maintained PySpark-based ETL pipelines to process customer usage, billing, and interaction data for downstream predictive modeling. Developed machine learning models for churn prediction, customer segmentation, and ARPU forecasting using Python (scikit-learn, TensorFlow). Designed feature stores and transformation logic in SQL to standardize data inputs for model training and validation. Automated data extraction, preprocessing, and scoring workflows using Airflow DAGs and shell scripts to ensure repeatable production runs. Implemented model monitoring and retraining triggers based on data drift and performance degradation using Python-based automation. Collaborated with marketing and operations teams to translate predictive insights into retention strategies and campaign targeting. Deployed models as RESTful APIs using Flask and Docker, integrating outputs with internal analytics dashboards Performed hyperparameter tuning, cross-validation, and model explainability studies to improve prediction accuracy and transparency. Supported migration of analytical workloads from on-prem Hadoop to early Databricks and cloud-based infrastructure for scalability and maintainability. Environment: Snowflake, PySpark, AWS EMR, SageMaker, Redshift, Lambda, Step Functions, SQL, Python, scikit-learn, XGBoost, TensorFlow, Tableau, QuickSight, GitHub, AWS Glue, Confluence Client: Cygnet Infotech, Hyderabad , India Role: Data Analyst Duration: June 2016 September 2019 Project Scope: Built analytics dashboards and automated reporting workflows to solve real customer-service challenges tracking SLAs, reducing escalations, and improving NPS/CSAT insights for operations teams. Analyzed customer-service and product-usage data to identify trends in resolution times, escalation rates, and recurring issue categories for performance optimization Created interactive Power BI and QlikView dashboards tracking SLA compliance, customer-satisfaction metrics, and agent-level performance KPIs used by operations leadership Developed Excel-based reconciliation reports to track monthly billing discrepancies, refunds, and invoice-level anomalies, ensuring financial accuracy and transparency Collaborated with business teams to define KPI logic and automated weekly / monthly reporting using SQL queries and Excel macros, improving report turnaround time Built user-friendly Excel dashboards with PivotTables, slicers, and conditional formatting to help non-technical stakeholders filter data by region, agent, or issue type. Partnered with QA and product teams to categorize issues by severity and frequency, helping prioritize bug fixes and product enhancements Designed scorecards and ranking charts to visualize weekly NPS, CSAT, and agent-level satisfaction metrics for performance reviews Supported quarterly business reviews by preparing trend analyses and visual summaries of performance metrics, customer feedback, and SLA attainment Environment: SQL, Power BI, QlikView, Excel, PivotTables, VLOOKUP, Excel Macros, Slicers, Conditional Formatting, Customer Support KPIs, NPS, CSAT, SLA Metrics EDUCATION ________________________________________ Bachelor of Technology (B. Tech) in Information Technology KLUniversity May 2016 Vijayawada, Andhra Pradesh, India Keywords: continuous integration continuous deployment quality analyst artificial intelligence machine learning business intelligence Georgia Illinois North Carolina