AI Software Engineer with experience in AI/ML systems and cloud-native solutions using Azure and AWS. Proven track record of designing, developing, and optimizing AI-driven applications and model deployment for scalable, high-performance services. Skilled in working with Large Language Models (LLMs), Generative AI (GenAI), and Retrieval-Augmented Generation (RAG), ensuring security and compliance in the cloud environment. Demonstrated expertise in CI/CD pipelines, infrastructure as code, and cloud-based AI models that meet reliability, safety, and scalability standards.

Currently working as a Software Test Engineer at LinkedIn, focusing on testing and validating cloud-native AI solutions. Completed my Master's degree in Computer Science at California State University, Fullerton in 2024.

• Focused on testing and validating cloud-native AI solutions deployed using Azure and AWS cloud services, ensuring security-first design principles for the systems

• Integrated cloud workflows and data pipelines (Azure Blob) to validate AI/ML models used for real-time predictions, ensuring accuracy, scalability, and audit readiness for AI-driven services

• Created test cases for AI-driven apps leveraging Azure AI Search and OpenAI APIs, validating context accuracy and summarization quality using BLEU and ROUGE scores

• Improved model deployment processes by automating workflows for continuous testing using Azure DevOps Pipelines, reducing deployment time by 40%

• Delivered high-performance, maintainable Java and Python code, reducing processing time by 55% and significantly improving system efficiency and user experience

• Engineered an LLM-powered chatbot using Azure AI Search, OpenAI APIs, and RAG pipelines, boosting engagement by 40%, reducing query time by 30% while ensuring seamless integration for future AI/ML model deployment

• Integrated advanced APIs, improving system responsiveness by 25% and contributed to the scaling of the application across multiple platforms

• Developed a LangChain and Azure OpenAI pipeline to convert website content into embeddings and store them in a Chroma vector database, enabling real-time, context-aware Q&A with custom prompt engineering

• Worked on LLM with LangChain and OpenAI, improving model responses through advanced prompt engineering and embedding generation

• Built data pipelines for vector search and embedding model, integrating them into the overall AI workflow to improve retrieval and response accuracy

• Optimized deployment of AI models by 35% using containerized solutions in Docker and Kubernetes

• Led the development of a cloud-native AI recommendation engine, utilizing Azure ML Studio for training and deployment. Integrated Azure AI and OpenAI APIs to enhance model inference accuracy and achieve real-time, scalable recommendations.

• Assisted in faculty-led research on app structure and scalability for AI/ML systems.

• Applied cloud-native AI APIs to enhance model accuracy and achieve real-time, scalable recommendations.

• Instructed 180+ students in AI/ML, database, and OOP concepts while assisting in faculty‑led research on app structure and scalability for AI/ML systems.

• Analyzed and developed new tutoring methods with various materials for students at university. Collaborated with teaching teams on debugging problems, reviewing, and writing optimized readable code.

• Lectured, directed exams, and prepared lessons for students on web frontend technologies such as flexbox, Grid, JavaScript, React.js, Transitions, Transform and Animation.

🚀 Context-Aware Retrieval → Integrated Azure AI Search with OpenAI APIs for human‑like, knowledge‑grounded answers

💡 Smarter Responses → Optimized LLM performance with custom prompt engineering and fine-tuning, reducing latency by 30%

⚙️ RAG Pipeline in Action → LangChain + Azure AI Search powering real-time retrieval-augmented generation

🔗 End-to-End Deployment → CI/CD pipelines with Azure DevOps ensuring seamless updates and production-ready AI delivery

Advanced AI/ML project showcasing expertise in Large Language Models and cloud-native AI solutions

Built a RAG app that can turn any website into a real-time Q&A system

🚀 From URL to Knowledge Base → converts any website into an interactive AI assistant

💡 Ask questions directly from a live webpage

⚙️ Developed a LangChain + Azure OpenAI RAG pipeline that transforms websites into Q&A-ready datasets

🔗 End-to-end AI project: Website → Embeddings → Vector Store → GPT‑4 powered answers

Built and deployed a fraud detection system on Azure ML, improving real-time fraud detection and reducing false positives by 20%. Applied Azure AutoML for hyperparameter tuning and feature engineering, optimizing model accuracy for real-time financial data.

Deployed the model using Azure Kubernetes Service (AKS) to handle multi-region, scalable deployment. Integrated advanced machine learning techniques for predictive analytics in financial fraud detection.