Portfolio · Rev. 2026.08

Federico Iglesias

Role: AI engineer
Based: Montevideo, Uruguay (UTC−3)
Now: Larson Labs, a venture studio
Stack: TypeScript, React, Next.js, Node, Python

I'm an AI engineer with a Computer Science degree from Universidad ORT Uruguay. I've spent the last few years building full-stack products — React, Next.js, TypeScript, Node, Python — and, more recently, LLM-based ones.

Email me See the work

1.0

How I work

I plan before I build. Most of what makes a product work or fail is decided in the architecture, so I spend the time up front on how the pieces fit. Then I move fast, with AI coding tools like Claude Code and Codex doing the typing.

I write the specs together with the people who need the product, get something running early, and put it in front of them instead of describing it.

Read 1.0 in full →

2.0

Work

Larson Labs

Software Engineer & R&D

2025 - Present
Remote

Build the studio's products end to end with the founders — first spec, production, and the day-to-day running of them, with AI coding agents in the toolchain.
Deal intelligence: scrapers across several marketplaces feeding LLM pipelines where specialist models read, score and summarise everything that lands.
Portfolio tooling: an options system that prices calls against live chains at a target delta, and a backtester run over a decade of point-in-time index membership.
Ops platforms on Next.js, Supabase and Postgres, with the cloud infrastructure underneath.

Full-Stack DevelopmentFinTechPortfolio ManagementR&DAI

Aurora Ideas

Founder & Head AI Engineer

2024 - 2024
Montevideo, Uruguay

Drove technological innovation and AI strategy across the organization
Built scalable AI systems using Python, LangChain, and modern frameworks
Developed UX/UI user-centric AI products

AIPythonLangChainNext.js

Effectus Software

Software Engineer

2020 - 2024
Montevideo, Uruguay

Built full-stack web and mobile applications using React, React Native, and Node.js
Led projects and collaborated with clients to ensure successful outcomes
On contract at String and Key in New York through 2022 and 2023, on the front end of wysh
Published and maintained applications on App Store and Google Play

ReactReact NativeNode.jsTypeScript

3.0

Selected projects

All 9 →

UruguAi Legal (now The Legal Tool)

Jan 2024 - Present

Chat-style research assistant for lawyers in Uruguay. Ask a legal question in plain language and get an answer with citations to the rulings and statutes it's based on. Also transcribes legal documents and calculates procedural deadlines. 1,250+ users since launch; the product has since been rebranded as The Legal Tool.

AILangChainPythonNext.jsReactTypescript

Read the write-up →

Expert Lawyer AI Agent

End to end (2023)

WhatsApp agent for a law firm. It answers prospective clients' questions, does a first pass on their case, and books Google Meet calls directly on the lawyers' calendars. Handles 1,400+ leads and schedules 140+ meetings a month, saving the firm 60+ hours of admin work.

NodeLangChainWhatsappAI

Read the write-up →

wysh

Contract via Effectus at String and Key, 2022-2023

US insurer selling term life and accidental death coverage entirely online, with no medical exam. A product company with large engineering teams, where I worked on the front end: the customer-facing web app in React and TypeScript on a GraphQL API.

ReactTypescriptGraphQL

Read the write-up →

Ahorrin

Oct 2025 - Present

Personal-finance coach for Uruguay. Upload a bank statement — CSV, Excel, PDF, OFX or QIF — and every transaction is categorised by GPT-4, then charted by month and category, with a chat assistant that answers questions about your own spending. Next.js 15, React 19 and Supabase, with landing pages written for each of the local banks.

Next.jsReactTypescriptSupabaseOpenAI

Open ahorrin.app ↗

View source ↗

The Tennis Almanac

2025 - 2026

An archive of 34 ATP seasons, and a statistic that argues with the sport. Break points saved is quoted as a measure of nerve, but across 472 careers it tracks ordinary serve quality with an R² of 0.81 — it mostly measures how hard you serve. The Clutch Index strips that out and ranks what is left, finding that reaching the world's top five is worth about two points of clutch on a hundred-point scale. Built from 93,720 matches; 3,950 prerendered pages, no server and no client framework.

AstroTypescriptData AnalysisStatisticsCloudflare

Open tenis-app.pages.dev ↗

View source ↗

4.0