Anas Raza Aslam

• Delivered hands-on Data Mining labs covering preprocessing, feature engineering, modeling, and evaluation using Python (Pandas, NumPy, scikit-learn)
• Conducted Cloud Computing labs on GCP (Compute Engine, Cloud Run, IAM, networking)
• Guided deployment of containerized applications (Docker) with scalable, cloud-native workflows
• Supervised projects on data pipelines, REST APIs, and ML systems aligned with industry practices
• Mentored students on cloud architecture and real-world deployment strategies

• Developed an end-to-end AI recruitment platform with automated CV parsing and candidate matching using LLMs (Qwen, LLaMA, Gemma).
• Designed and implemented an MLOps pipeline for model serving, including data preprocessing, inference APIs, and deployment workflows.
• Built scalable REST APIs using FastAPI for real-time resume parsing and candidate recommendation.
• Containerized applications using Docker and deployed on Google Cloud Platform (Compute Engine).
• Implemented auto-scaling and cost optimization strategies (scale-to-zero hosting) for efficient model serving.
• Integrated CI/CD workflows for continuous integration and deployment of model services.
• Utilized SQL/NoSQL databases for structured data storage and optimized query performance.
• Ensured code modularity, logging, and monitoring for production reliability and maintainability.
• Applied model versioning and experiment tracking practices to improve reproducibility and performance monitoring.

A comprehensive health insurance comparison platform that leverages cutting-edge RAG (Retrieval-Augmented Generation) technology to provide personalized insurance recommendations.

Key Features

• Developed an AI-powered health insurance recommendation platform using Retrieval-Augmented Generation (RAG) for personalized policy suggestions.
• Built end-to-end pipelines for data ingestion, preprocessing, embedding generation, and retrieval using vector databases (Chroma DB).
• Integrated LLMs (OpenAI GPT / open-source models) to generate contextual and user-specific recommendations.
• Designed scalable backend APIs using FastAPI for real-time query handling and recommendations.
• Implemented MLOps workflows including model serving, pipeline automation, and deployment lifecycle management.
• Containerized the application using Docker and deployed on cloud infrastructure for production-ready usage.
• Applied model versioning and embedding updates to maintain consistency and improve recommendation quality.
• Monitored system performance and optimized latency and response time for real-time user interaction.
• Developed a full-stack solution with React.js frontend, enabling dynamic user interaction and visualization.