Xavier Puspus
AI Architecture and Engineering
About
I work end-to-end on AI systems and the tooling around them: retrieval, evaluation, cloud infrastructure described in natural language, civic-data, and image forensics. Comfortable from data ingest through backend services to a polished frontend. Mostly Python and TypeScript. Physicist by training.
Technical stack
- Languages
- Python, TypeScript, JavaScript, SQL
- AI / ML
- LangGraph, MCP, OpenAI SDK, Anthropic SDK, scikit-learn, PyTorch, Transformers
- Retrieval
- Vector stores, contextual retrieval, RAPTOR, PageIndex, knowledge graphs, hybrid
- Backend
- FastAPI, Flask, Postgres
- Frontend
- Astro, Next.js, React, Tailwind
- Infra
- AWS, Netlify, Docker, GitHub Actions
- Domains
- Retrieval evaluation, civic data, fraud detection, image forensics, NLP, fairness, RAG
Featured projects
- cloudwright Python · ★ 29
AI-powered cloud architecture - describe infrastructure in natural language, get Terraform, cost estimates, and compliance reports
- kb-arena Python · ★ 7
Benchmark 7 retrieval strategies on your own docs , naive vector, contextual, QnA pairs, knowledge graph, RAPTOR, PageIndex, and hybrid. Find which KB architecture fits your data.
- ai-workflow-benchmark Python · ★ 9
Benchmark harness measuring AI coding tool+workflow performance, not just model capability. 100 tasks, sigmoid scoring, 12 capability dimensions, gap analysis.
- ph-civic-data-mcp Python · ★ 0
The first multi-source MCP server for Philippine civic data: earthquakes, weather, typhoons, procurement, population, poverty
- paper-trail-ph Python · ★ 2
Philippine Public Accountability Graph
- solar-map-ph Python · ★ 0
Open-source rooftop solar detection from public satellite imagery. CLIP-ViT-L + logistic regression, Platt-calibrated, deterministic Docker build. Coverage: Greater Metro Manila. Free homeowner roof-lookup tool, CC-BY-4.0 data, MIT code.
Selected open source
AI safety and forensics
- parity-fairness Measure bias from data and machine learning models. Python
- fraud-detection-ids Error level analysis and noise analysis on government IDs. Python
Document AI and chat tooling
- ChatPDF Web app to chat with any PDF. Python
- ChatWEB Web app to chat with parseable websites. Python
- ChatCSV Web app to chat with your CSV. Python
- auto-question-generation Generate questions and possible answers from input text or URL. Jupyter Notebook
- ZeroShotClassification Text classification with minimal data, custom labels and context. Jupyter Notebook
- gpt2_text_completion Web application for text completion using GPT2. Python
Civic and Philippine open data
- ghostwatch Satellite verification of government infrastructure. Python
- spend-watch-ph AI-powered monitoring of government spending. TypeScript
- AIforSEA Submission to the Grab Safety Challenge. Jupyter Notebook
On-device and offline AI
- airgap Air-gapped AI customer support. On-device LLM, offline-first, config-driven, 7 industry templates. TypeScript
Generative tools and agents
- ai-leetcode-solver Solve LeetCode problems from screenshots via GPT. JavaScript
- ai-instagram-caption-generator Upload an image, generate Instagram captions. JavaScript
- ai-company-search GPT-driven search for company metadata. JavaScript
Domain ML and applied modelling
- aedes Mosquito-borne disease modelling for project AEDES. Jupyter Notebook
- pads Precision agriculture and data science in the Philippines. Jupyter Notebook
- Earthquake-Analysis M6+ earthquake count analysis, bar-chart-race prep, and forecasting attempts. Jupyter Notebook
- news-image-classifier-webapp Image-based news classifier (fake / good / bad / sports / science). Python
- NLP-transfer-learning Custom named-entity recognition via transfer learning. Jupyter Notebook
- pricing-webapp Pricing model deployed as a web application. Jupyter Notebook
- review-rating-predictor-webapp Predict review rating from text. Jupyter Notebook
- dow-jones-sentiment-predictor-webapp Stock direction prediction from news article sentiment. Jupyter Notebook
- census-income-webapp Income-bracket prediction deployed as a web app. Jupyter Notebook
- advertising-webapp Sales forecast model deployed as a web app. Jupyter Notebook
Full list of 59 repositories at /projects .
Education
- BS Applied Physics, University of the Philippines Diliman
- MS Applied Business Analytics, University of Asia and the Pacific