I bring AI agents into production. Working with enterprises to move from experiments to mission-critical deployments — deep integrations, real workflows, real impact.
Currently a Forward Deployed Engineer at Wonderful.ai — the enterprise agent platform. I help large companies move AI agents from concept into production: deep integrations with CRM, ERP and internal systems, agent configuration across languages and regulatory contexts, and post-deployment monitoring.
Before that, three years at Accenture Industry X — most recently as Senior Software Engineer. Owned backend features for a mission-critical medical platform, improved API performance up to 70%, defined architectures from scratch, and led international teams across Italy and India.
Earlier I worked on Deep Learning research with a focus on Computer Vision — GANs for synthetic data generation, CNNs for image classification, and applied ML projects bridging research and shipped products.
Helping enterprises move AI agents from concept to production. Work spans deep integration with internal systems (CRM, ERP, core banking), agent configuration tailored to each market's language, regulatory and cultural context, and post-deployment monitoring and optimization. Forward-deployed engineering at the edge of agentic AI.
Co-founded the open-source SDK that gives AI agents a phone number. Conducted 200+ calls with customers, developers and startups. Grew Patter to 1,000+ GitHub stars, 126 forks and 9 contributors, attracting contributions from engineers at Telnyx, Plivo (YC), Resemble AI, and more. Today, hundreds of people actively use it in production.
Product-oriented engineer with end-to-end ownership of backend and AI-powered products. Working on a mission-critical medical platform, improving API performance up to 70%, defining backend architectures from scratch, and delivering features in international team settings.
Owned backend features for a mission-critical medical order management system with strict reliability requirements. Led international feature teams across Italy & India, ensuring deadlines in a regulated, high-pressure environment. Built internal GenAI tools to support code reviews and improve team development speed.
Contributed to backend development and Python-based computer-vision projects. Supported data collection and labelling pipelines for model training and evaluation. Worked across multiple microservices, ensuring stable contracts and integrations.
AI-powered applications that extend human capabilities.
An open-source SDK that gives AI agents a phone number — connecting any agent to real phone calls in 4 lines of code. Python and TypeScript at parity, MIT licensed, sub-500ms time-to-first-audio. Pluggable across 27+ providers including OpenAI Realtime, Anthropic, Deepgram, ElevenLabs, Twilio and Telnyx.
An Electron desktop app (TypeScript, React) providing a unified AI-driven workspace. The Node.js / TypeScript backend handles reasoning, state and orchestration; external services are wired through MCP servers (OAuth2, gRPC/HTTP, JSON-RPC) to expose email, calendar and other APIs in a secure, standardized way.
First-prize winner at the MCP Apps hackathon in Turin, sponsored by Manufact. An AI-powered personal agent with a centralized memory layer. Create your Digital Twin, collaborate with friends' Twins via MCP, and access your plans and memories from any AI client — ChatGPT, Claude Code, or your own apps. Built with TypeScript and Supabase.
AI travel companion that talks, searches and calls restaurants for you. Voice chat to discover places, view interactive cards with photos and ratings, and let the AI make phone calls in 15 languages. Built with SwiftUI, ElevenLabs Conversational AI, Firecrawl, Google Places API, and Twilio.
An MCP server that orchestrates debates among five AI agents with distinct personalities — Strategist, Pragmatist, Critic, Innovator, Philosopher. Users pose complex questions, and the agents deliberate across structured rounds (Proposal, Critique, Refinement, Vote) before reaching consensus. Built with TypeScript, the mcp-use framework, and the OpenAI Apps SDK, with a live-streaming React widget for real-time visualization.
An AI keyboard for iOS that lets users leverage AI directly from their iPhone keyboard. Create personalized messages, rewrite content, and auto-respond across any application.
An AI-powered app that turns hours of YouTube videos into minutes of actionable insights. Features comprehensive summaries, full transcripts, and key-quote extraction.
Machine-learning research and software-engineering projects.
Research project exploring how GAN-generated synthetic data can improve CNN classification accuracy in low-data scenarios. Part of the International Master thesis.
A deep-learning project implementing Convolutional Neural Networks for satellite image classification, enabling automated land-use analysis.
Hardware projects combining mechanical engineering with software.
Currently suspended. The final vision: mount a camera on the arm and use AI image-recognition with motors driven via Arduino, so the AI controls the robot to play backgammon against a real person.
I'm always interested in discussing new projects, creative ideas, or opportunities to be part of your vision. Whether you have a question or just want to say hi — feel free to reach out.
