Fernando Carril is an AI Full-Stack Engineer with 14+ years of experience building end-to-end web products, specializing in TypeScript/React frontends and Node.js backends while ramping into Go and Rust for production systems. He’s shipped LLM-powered features, evaluation and observability tooling—leading the open-source Opik frontend and crafting SDKs and integrations used to debug and monitor RAG/agent workflows. Comfortable in remote, async environments across US/EU startups, he has scaled frontend teams and owned architecture, product delivery, and developer-facing UX that teams actually adopt. Fernando excels at real-time, data-heavy UIs, performance work, and developer SDKs, and he integrates AI-assisted coding (Claude Code) into his engineering loop to speed delivery. Current focus is on deploying LLM agents in production with Vercel AI SDK and building measurable AI-native products as a Staff-level FE / Full-Stack engineer. Based in Barcelona, he combines hands-on implementation with cross-functional leadership and a track record of turning evaluation and tracing needs into production-ready dashboards.
14 years of coding experience
14 years of employment as a software developer
Computer Systems Analyst Computer Systems Analysis/Analyst, Computer Systems Analyst Computer Systems Analysis/Analyst at ORT Institute
Electronic Technician Industrial Electronics Technology/Technician, Electronic Technician Industrial Electronics Technology/Technician at Technical High School Nº9 of Lanús
Computer Engineering Computer Engineering, Computer Engineering Computer Engineering at Universidad del CEMA
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
Role in this project:
Front-end Developer
Contributions:209 reviews, 262 PRs, 256 pushes in 1 year 8 months
Contributions summary:Fernando primarily focused on front-end development tasks, making significant changes to the user interface and application layout. They modified the "Get Started" page layout and added new UI components for displaying dataset item counts and for handling trace limits. The user also addressed image handling by truncating base64 images and enabling their display within the application. Furthermore, the user removed colab links from the quickstart in the sagemaker integration, modifying the quickstart page.
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.