💡 Current Focus: AI Infrastructure
Currently developing a microservice for local LLM inference using vLLM to analyze government contracts. My goal is to apply high-load engineering principles to make AI efficient and scalable.
Building mission-critical systems that cannot fail.
Specializing in national-scale monitoring and high-throughput data streams with sub-200ms latency.
Deep expertise in the Kotlin & Java ecosystem, building robust and maintainable services.
Based in Barcelona (CET). Ready for B2B/Contract work via US LLC (Wyoming).
National Oncology Monitoring
Architected backend for millions of patients with 99.9% availability.
SQL & Graph Improvements
Optimized reporting modules, reducing generation time by 40%.
Low Latency APIs
Designed APIs handling sensitive medical records with sub-200ms latency.
Java to Kotlin Migration
Led migration reducing production bugs by 20%.
Currently developing a microservice for local LLM inference using vLLM to analyze government contracts. My goal is to apply high-load engineering principles to make AI efficient and scalable.
Looking for Backend or AI Engineering roles where performance matters.