Skip to content
View D0men1c0's full-sized avatar
🎯
Focusing
🎯
Focusing

Highlights

  • Pro

Block or report D0men1c0

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
D0men1c0/README.MD

Domenico Lacavalla

Applied Scientist & AI Researcher — LLMs, RAG, NLP, interpretability, multimodal AI.

EmailLinkedInGitHubHugging FaceMedium


About

I work at the intersection of research and production AI, building systems that are both effective and measurable.

My focus is on LLM evaluation, Retrieval-Augmented Generation, model interpretability, and multimodal pipelines — with a particular interest in making AI systems understandable, not just functional.

Currently at Leonardo Labs as an AI Researcher & Applied Scientist. Previously at IBM and Google Summer of Code 2024 (HumanAI).


Experience

Leonardo Labs — AI Researcher & AI Applied Scientist
Agentic AI safety, RAG evaluation, and interpretability workflows for assessing model transparency and robustness.

IBM — Data Scientist & Applied Scientist
Multimodal retrieval, anomaly detection, summarization, geospatial intelligence, and production NLP systems.

Google Summer of Code 2024 — HumanAI — Open Source Contributor
Open-source NLP research on large-scale Dark Web analysis, including topic extraction, clustering validation, and multimodal labeling workflows.


Areas of Interest

LLMs RAG NLP Multimodal AI Computer Vision Interpretability AI Evaluation


GitHub Activity

Pinned Loading

  1. humanai-foundation/ISSR humanai-foundation/ISSR Public

    Jupyter Notebook 6 30

  2. bralani/text2motion bralani/text2motion Public

    Python 5 1

  3. Benchmark-Gemma-Models Benchmark-Gemma-Models Public

    Highly customizable Python suite for LLM evaluation (Gemma, LLaMA+). Full custom script integration for models, datasets, tasks & metrics. Resource-friendly.

    Python 5

  4. Knowledge-Injection-XAI Knowledge-Injection-XAI Public

    Distributed framework for selecting Vision Transformer adapters using explainability metrics

    Jupyter Notebook