Browse Projects
Browse projects tagged with "LLM".
AI Portfolio Assistant
WebI built a conversational AI assistant directly into my portfolio site. Recruiters and visitors can ask anything about my projects, skills, and background — and get grounded, cited answers in real time, powered by RAG (Retrieval-Augmented Generation) and Llama 3.3 70B via Groq.
AWS Lambda & Amazon Bedrock: Benchmarking TF-IDF, LSTM, and Zero-Shot LLM Sentiment Analysis
Ai-mlA full ML pipeline benchmarking TF-IDF + Logistic Regression, a Keras LSTM, and Claude Haiku via Amazon Bedrock on 50,000 IMDb reviews. The winning model is deployed live as a serverless REST API on AWS Lambda with a Flask frontend.
CV Gap Analyser — Semantic Job Matching with HuggingFace and Pinecone
Ai-mlSemantic CV vs job description analysis identifying missing skills and producingactionable gap recommendations. HuggingFace embeddings for match scoring, Pineconefor a searchable job library, ROUGE for ATS keyword alignment. Accepts jobdescriptions as text, PDF, or URL via trafilatura extraction.
LLM Document Summarizer — LLMOps with Amazon Bedrock
Ai-mlPDF document summarizer using Amazon Bedrock (Claude Haiku) with production LLMOps patterns: versioned YAML prompt templates, automated ROUGE evaluation, Bedrock Guardrails for PII redaction, and MLflow tracking of every inference call. Deployed on Azure App Service.
Professional Portfolio Site
WebFull-stack Flask portfolio with a custom admin dashboard, PostgreSQL, a REST API, an AI assistant powered by RAG, Cloudflare R2 media storage, and CI/CD deployment to Railway via GitHub Actions.
Stock Trend Pattern Recognition — Amazon SageMaker MLOps
Ai-mlStacked LSTM for stock trend pattern detection, served via Amazon SageMaker Real-Time Endpoint. Flask frontend on Azure App Service — multi-cloud MLOps. Pattern detection only, not financial advice.
Telco Customer Churn Predictor
DataChurn prediction with plain-language risk explanations a retention team can act on. Logistic Regression wins (ROC-AUC 0.8362), benchmarked against Amazon Bedrock Claude Haiku 4.5 zero-shot — tied at 70%. Flask API on Azure.
Workout Tracker
SoftwareLog workouts to Google Sheets using plain English. A local LLM parses your session, calories are calculated via the MET formula, and each exercise is written as a timestamped row — no manual entry.
No projects found
No projects match the current filter.