# Matteo Pesenti

> University of Waterloo software engineering student with experience building backend systems, full-stack features, and AI-powered tools at Fable Security, Carta, Adentro, and Sizzle AI.

## Summary

- Role: Software Engineer (backend, full-stack, AI)
- Education: Bachelor of Software Engineering, University of Waterloo (graduating April 2027)
- Location: New York, NY
- Looking for: Targeting US full-time backend, full-stack, and AI software engineering roles. Most effective on teams where product quality, system reliability, and shipping speed all matter.
- Internships: 5, at Fable Security, Carta, Adentro, National Research Council Canada, Sizzle AI

## Experience

### Software Engineer Intern — HRM Data Platform, Fable Security

San Francisco, CA · 2026-05 to 2026-08 · Python, Django, React, Terraform, Kubernetes, Airflow, MCP, AI Agents

- Worked directly with customers to build human risk scoring, a Django + React model that flags where a company's risk is coming from, unblocking 9 enterprise deals worth $2M in ARR.
- Architected an internal MCP platform in Django + Terraform that gives AI agents PII-masked, audited access to production data, Airflow, and Kubernetes to diagnose failures, cutting failed pipeline runs from 12% to 0%.
- Engineered an AI agent that autonomously resolves production incidents, restarting failed DAGs, opening fix PRs, and suppressing noisy alerts, cutting manual intervention by 65%.
- Set up cloud dev environments that give engineers and coding agents a running copy of the app to work in, so agents can build and test changes in parallel, driving 30% more PRs.

### Software Engineer Intern — Investor Experience, Carta

New York, NY · 2026-01 to 2026-04 · Python, Django, Celery, React, TypeScript, LLM Pipelines, Braintrust, Module Federation

- Built an LLM extraction pipeline that parses option grants and stock certificates from uploaded documents into structured cap table data, writing the prompts and extraction code, handling 1,400 extractions/day.
- Redesigned cap table extraction as a fully async experience in Django + Celery, tracking job status live and emailing users a deep link when results are ready, removing a 2-10 minute blocking wait.
- Designed Braintrust eval scorers that grade every prompt change against 100+ labeled documents, lifting extraction accuracy from 80% to 99.6%.
- Rebuilt the cap table importer and warrant-signing pages as React + TypeScript microfrontends with module federation, serving 12,000 weekly users.

### Software Engineer Intern — Core Product, Adentro

San Francisco, CA · 2025-05 to 2025-08 · Go, React, gRPC, REST APIs, PostgreSQL, AWS S3

- Implemented a customer portal editor in React + Go, building the UI and the REST and gRPC APIs that let businesses customize their WiFi portals, as part of a $5M ARR deal with Verizon.
- Integrated Foursquare, Google Places, and Yelp APIs with rate-limited, retrying clients to enrich venue metadata powering audience segmentation across millions of WiFi users.
- Built a React component for dynamic captive-portal ads backed by gRPC services querying PostgreSQL and S3, enabling targeted campaigns.
- Created a Go testing framework for PostgreSQL with schema cloning and parallel CI execution.

### Software Engineer Intern — Building and Climate Interface, National Research Council Canada

Ottawa, ON · 2024-09 to 2024-12 · Python, Flask, React, Qt, GIS

- Developed a React + Flask wildfire hazard-mapping tool, building the map UI and serving geospatial data through REST APIs, cutting hazard assessment from days to minutes.
- Developed a Python + Qt desktop tool to disseminate wildfire-resilient building guidelines, integrating hazard, exposure, and construction GIS data.

### Software Engineer Intern, Sizzle AI

New York, NY · 2024-01 to 2024-04 · Python, FastAPI, React, PyTorch, Baseten

- Built diagram solving in FastAPI + React for photographed homework problems, fine-tuning a PyTorch classifier on 10,000 labeled images to detect diagrams, lifting engagement 8% in A/B tests.
- Migrated ML services from Hugging Face to Baseten, reducing latency spikes by 30% across 20+ production models.

## Projects

- [PokerGPT](https://github.com/matteo-psnt/PokerGPT): A Discord bot that plays heads-up Texas Hold'em against you, powered by GPT-4. Used by 8,000+ players across 3,000+ servers. (Python, Discord.py, OpenAI GPT-4, MySQL, LangChain) · Demo: https://discord.com/oauth2/authorize?client_id=1102638957713432708&permissions=277025773568&scope=bot%20applications.commands
- [Blackjack](https://github.com/matteo-psnt/blackjack): Casino blackjack in the browser, with chip betting and card animations. Playable right here on the site. (React, TypeScript, Zustand, Framer Motion, Tailwind CSS) · Demo: https://www.matteopsnt.dev/blackjack
- [Wordle Solver](https://github.com/matteo-psnt/wordle-solver): Plays the daily Wordle by itself, using a word-selection algorithm to pick each guess. (Python, Selenium, Web Scraping, Algorithm Design)
- [Poker Replay](https://github.com/LukasMartini/poker-replay): Upload your poker hand histories, then replay and analyze each hand visually. (React, PostgreSQL, Express, Python, Flask, Docker) · Demo: http://repl.poker/
- [Chess AI](https://github.com/matteo-psnt/chess): A C++ chess engine with a graphical board, full move validation, and AI opponents at several difficulty levels. (C++, SFML, AI Algorithm)

## Skills

Python, React, Django, TypeScript, PostgreSQL, Flask, Terraform, Kubernetes, Airflow, MCP, AI Agents, Celery, LLM Pipelines, Braintrust, Module Federation, Go, gRPC, REST APIs, AWS S3, Qt, GIS, FastAPI, PyTorch, Baseten, Discord.py, OpenAI GPT-4, MySQL, LangChain, Zustand, Framer Motion, Tailwind CSS, Selenium, Web Scraping, Algorithm Design, Express, Docker, C++, SFML, AI Algorithm

## Links

- [Résumé (PDF)](https://www.matteopsnt.dev/Matteo_Pesenti_Resume.pdf)
- [Website](https://www.matteopsnt.dev/)
- [GitHub](https://github.com/matteo-psnt)
- [LinkedIn](https://www.linkedin.com/in/matteo-pesenti/)
- Email: matteopesenti229@gmail.com