Research Engineer · AI MSc @ University of Amsterdam · RL, world models, LLM evaluation, efficient inference
Website · Email · LinkedIn · Google Scholar · CV
I'm Francesco, a research engineer and AI MSc student at the University of Amsterdam with a background in software engineering and machine learning research.
I like building things that sit between research and engineering: reproducible ML pipelines, model evaluation setups, world-model experiments, and tools that make results easier to inspect, explain, or deploy. Lately I'm increasingly interested in efficient inference — making models faster and cheaper to serve.
Recently, I have been working on:
- reinforcement learning and hierarchical planning with latent world models — accepted @ WM@Booth (Workshop on World Models, Chicago Booth 2026)
- probing video foundation models for intuitive physics — arXiv:2606.09646
- open-weight LLM safety evaluation and dataset filtering
- ML pipelines for Multiple Sclerosis biomarker discovery — first author, arXiv:2603.05572
Before focusing more deeply on AI research, I worked as a full-stack developer, building production web platforms with React, Node.js, PostgreSQL, Docker, and Linux deployments.
A research project on hierarchical planning for goal-conditioned control using latent macro-actions, CEM/MPC planning, and a frozen low-level world model. Accepted at WM@Booth 2026.
Layerwise probing of V-JEPA, VideoMAE, and LTX-Video representations to study whether pretrained video models encode intuitive-physics structure.
Reproduction and extension of harmful-content filtering pipelines for web-scale datasets using open-weight LLMs and moderation benchmarks.
Machine learning pipeline for transcriptomics analysis, combining XGBoost, SHAP, differential expression analysis, and biological enrichment. First author, arXiv:2603.05572.
AI / ML
Software engineering
You can reach me at massafra32@gmail.com or connect with me on LinkedIn. More at firewtap.github.io.