AI Engineer & Researcher 🏆 EMNLP 2023 Outstanding Paper Award 🎓 MSc CS Engineering @ Politecnico di Milano 🔬 LLM Evaluation · Agentic Systems · MLOps
AI-Atlas score
| Machine Learning | 39 |
|---|---|
| Computer Vision | 0 |
| Data Science | 9 |
| NLP & LLMs | 54 |
| AI Agents | 44 |
| MLOps | 34 |
Each node is one domain, scored only from evidence in these public repositories. Select one to see why.
Substantial implementations with real depth.
8 public repositories → 3 with AI work, evaluated. The other 5 (repositories without AI code, forks and empty repositories) are not scored and have no effect on the result. How repositories are selected
Ordered by how much each project adds to the Atlas score, not by its own score. A project with evidence in several domains can rank above one with a slightly higher project score. Choose a domain to focus on the projects with meaningful evidence there.
58% of Atlas Score
MedRAG Assist is a Retrieval-Augmented Generation (RAG) system for medical question answering, featuring a Flask web interface, document processing pipeline, and Docker-based deployment.
36% of Atlas Score
MultiMinds is a multi-agent AI assistant that uses LangChain, LangGraph, Groq, and Tavily for web search to provide research-oriented answers, featuring a FastAPI backend, Streamlit frontend, and Dockerized deployment.
6% of Atlas Score
The repository provides a starter package for a Hindi Linguistic Inquiry and Word Count (LIWC) analyzer, containing basic tokenization, normalization, and dictionary lookup functions but lacking the actual lexicon and advanced linguistic resources.
