Hi, I'm Filippo

Software Engineer, passionate about Generative AI, Multi-Agent Systems, Machine Learning, Distributed Systems and IoT. 🚀🤖✨

About Me

Hi! I'm Filippo, I'm currently working as a Software Engineer at Blue Reply IT.

October 2024 - Current

• Built a real-time clustering system for road events (accidents, construction, weather) powering (de)activation of autonomous driving features across 1M+ vehicles, with 85% latency reduction. Scaled to 30k+ daily events using Java, Spring Boot, and MongoDB on Kubernetes/AWS.
• Designed and deployed a multi-agent system with LangGraph and Python to automate end-to-end JUnit test generation from GitLab issues. Processed 50+ issues/month, saving ~60 QA hours/quarter; adopted by 2+ engineering teams within 3 months, fully replacing manual test workflows.

February 2022 - April 2022

• Developed modular web applications using Angular microfrontends, enabling independent deployment pipelines across feature teams.
• Implemented async data flows with RxJS streams and leveraged functional programming patterns (immutability, pure functions, monadic composition) to reduce side effects and improve code testability.

January 2018 - March 2018

• Evaluated and optimized the AI model for random circuit generation in the sandbox racing game RaceCraft, enhancing track diversity and player experience. Tested and fine-tuned hyperparameters for AI-driven automated drivers, resulting in smoother, more competitive, and adaptive racing behavior.

2022 - 2024

• 110/110 with Honors
• Thesis focused on decentralized multi-agent reinforcement learning via GNNs, leading to a published research paper.

September 2023 - February 2024

• Completed coursework in Computer Graphics, Virtual and Augmented Reality, Cognitive Interaction with Robots, and Normative and Dynamic Virtual Worlds, focused on real-time simulation, embodied interaction, and AI for games.
• Simulated particle, cloth, and fluid dynamics in C++ for real-time rendering.
• Built AR and VR apps in Unity, including mobile-based AR and room-scale VR, sustaining 60 FPS on consumer devices.
• Engineered a 3D investigation game with FSM-driven NPCs and AI behaviors, enabling 100% dynamic branching dialogue across 5+ suspect profiles.
• Developed a pose-matching browser game using Google MediaPipe and webcam-based real-time human pose estimation, achieving >90% classification accuracy and <100 ms latency on Chrome.

2019 - 2022

• 110/110 with Honors
• Thesis: built a real-time network architecture in Unity (C#) for collaborative Mixed Reality on HoloLens 2, supporting consistent multi-user state sync. Achieved <50 ms latency and 3,800 packets/sec throughput in high-entity-density scenarios over TCP and UDP.