Pragya Dhupia
AI/ML Engineer Gen AI
Mail: *************@*****.*** Phone No: 770-***-****
PROFESSIONAL SUMMARY
AI/ML Engineer with 4+ years of experience in Python, SQL, machine learning, Generative AI, and data analytics. Hands-on experience building ML models, RAG applications, LLM workflows, AI agents, and data pipelines using Python, Scikit-learn, XGBoost, LangChain, LangGraph, Databricks, Snowflake, and Spark. Experienced in developing end-to-end AI solutions including data preparation, feature engineering, model evaluation, embeddings, vector search, API development, MLOps, and model monitoring. Strong background in healthcare data, data quality, validation, reconciliation, and enterprise analytics, with experience collaborating with data scientists, engineers, and business stakeholders to deliver practical and production-ready AI/ML solutions.
CORE SKILLS
Languages & Data: Python, SQL, Pandas, NumPy, Excel
Machine Learning: Scikit-learn, XGBoost, Feature Engineering, Classification, Regression, Model Validation, Model Evaluation
Generative AI: LLMs, Prompt Engineering, RAG, Embeddings, Vector Search, LangChain, LangGraph, AI Agents
Data & Cloud: Databricks, Apache Spark, Snowflake, Structured & Unstructured Data, Data Pipelines
MLOps & Development: MLflow, FastAPI, Docker, Git, CI/CD, REST APIs, Automated Testing, Model Monitoring
Data Quality & Analytics: Data Quality, Data Validation, Data Cleansing, Data Reconciliation, Master Data Management, Reporting
AI Developer Tools: GitHub Copilot, AI Coding Assistants, Agentic AI Workflows, Prompt Engineering, LLM Tool Calling
AI-First Software Engineering: AI-Assisted Requirements Analysis, AI-Assisted Solution Design, AI Code Generation, Code Refactoring, AI-Assisted Debugging, AI-Driven Test Case Generation, Regression Testing, AI-Assisted Code Review, Technical Documentation Generation
PROFESSIONAL EXPERIENCE
AI/ML Engineer — Elevance Health NJ (Remote) Sep 2025 – Present
Project: AI Infrastructure & Generative AI Platform Engineering
•Designed and developed AI/ML solutions using Python, SQL, and modern machine learning frameworks to analyze healthcare and operational data and support enterprise business use cases.
•Built production-oriented Generative AI applications using LLMs, prompt engineering, embeddings, and Retrieval-Augmented Generation (RAG) to enable context-aware responses from structured and unstructured healthcare data.
•Developed end-to-end RAG pipelines covering document ingestion, chunking, embedding generation, vector indexing, semantic retrieval, prompt orchestration, and LLM-based response generation.
•Implemented AI agent workflows using LangGraph/LangChain with tool calling and multi-step reasoning patterns to automate data analysis and business processes.
•Integrated AI services with enterprise APIs, databases, and internal applications to deliver scalable AI capabilities across business workflows.
•Leveraged AI-assisted software engineering workflows to analyze business requirements, support technical design, generate implementation approaches, and accelerate end-to-end SDLC delivery.
•Established evaluation workflows to measure LLM and ML model quality using accuracy, precision, recall, F1-score, retrieval relevance, response quality, and other task-specific metrics.
•Applied Generative AI and prompt engineering techniques to assist with code generation, code explanation, refactoring, debugging, and development of maintainable Python applications.
•Applied Responsible AI practices including model evaluation, bias analysis, explainability, prompt validation, audit documentation, and monitoring of AI-generated outputs.
•Developed monitoring and observability processes for production AI/ML applications, tracking model performance, latency, failures, data quality, and system reliability.
•Supported MLOps workflows using MLflow, Docker, Git, and CI/CD practices for model versioning, deployment, experiment tracking, and lifecycle management.
•Optimized AI pipelines for scalability, response latency, reliability, and cloud resource utilization while maintaining model and application performance.
•Worked with structured and unstructured healthcare datasets stored in Snowflake/Databricks and developed data pipelines to prepare high-quality datasets for analytics and AI applications.
•Conducted experimentation and benchmarking across different ML models, LLMs, prompts, retrieval strategies, and embedding models to identify the most effective solution for each business use case.
•Collaborated with data scientists, software engineers, product teams, and healthcare business stakeholders to translate business requirements into production-ready AI/ML capabilities.
AI/ ML Engineer— Amgen GA Aug 2024 – May 2025
•Developed Python and SQL solutions for data processing, machine learning, and AI applications, with a focus on clean and maintainable code.
•Built and tested machine learning models using Scikit-learn and XGBoost for classification, regression, and prediction use cases.
•Performed data preparation, exploratory analysis, feature engineering, and model validation to improve the quality of ML results.
•Used cross-validation and model comparison techniques to select suitable algorithms and understand model performance and limitations.
•Developed GenAI applications using LLMs, prompt engineering, embeddings, and Retrieval-Augmented Generation (RAG).
•Applied prompt engineering and LLM-based workflows to support technical problem-solving, code analysis, data processing, and automation of repetitive development activities.
•Developed automated validation strategies for Python-based AI services, including functional checks, edge-case validation, API testing, and regression testing.
•Worked with structured and unstructured data using SQL, Python, Spark, and Databricks to prepare data for AI and ML applications.
•Developed and supported APIs and AI services using FastAPI and Docker, following basic testing, version control, and deployment practices.
•Used Git-based version control and CI/CD practices to support code integration, application testing, deployment readiness, and iterative improvements to AI/ML services.
•Used MLflow and CI/CD workflows to track experiments, manage model versions, and support deployment and ongoing model improvements.
•Monitored AI/ML applications for data issues, model performance, errors, and response quality, troubleshooting problems as they occurred in production.
•Worked closely with business users, data engineers, software developers, and other stakeholders to understand requirements and deliver practical AI/ML solutions.
Data Analyst — HCL Tech India Jun 2019– Jul 2021
•Maintained and updated customer, product, pricing, and vendor master data using MDM tools and MS Excel, ensuring accuracy, completeness, and consistency across business records.
•Analyzed master data using Excel, including filters, PivotTables, VLOOKUP/XLOOKUP, formulas, and data validation to identify missing, duplicate, and inconsistent records.
•Performed routine data quality checks and reconciled master data against source systems to identify discrepancies and support timely corrections.
•Prepared daily, weekly, and monthly reports using Excel and PowerPoint to monitor data quality, process status, and business performance.
•Analyzed recurring data issues and assisted in identifying root causes related to data entry, validation, and process gaps.
•Supported data cleansing and standardization activities for customer, product, pricing, and vendor records according to defined business rules.
•Documented business requirements, data issues, process steps, and proposed changes to support master data process improvements.
•Created and maintained process documentation, data validation guidelines, and standard operating procedures for routine data management activities.
•Collaborated with business users and team members to investigate data discrepancies, clarify requirements, and resolve routine master data issues.
•Assisted with user acceptance testing and validation of approved process changes to ensure master data remained accurate after implementation.
•Monitored data management workflows and communicated exceptions, trends, and unresolved issues to the appropriate team members.
•Supported continuous process improvement initiatives by analyzing repetitive manual activities and recommending straightforward improvements to data validation and reporting processes.
EDUCATION
Master’s College Name: Georgia State University, Atlanta, GA
Masters Completion Month and Year: Aug 2025