Cloud & DevOps Engineer//AI offensive security · LLM red teaming//Full Stack Engineer
whoami --verbose
Cloud & DevOps engineer at a cybersecurity product company in Donostia: R&D in exposure management and offensive security on a product that ships and runs in production. Before that, five years at an industrial scale-up shipping product to production —full stack (ML, WebRTC, PostgreSQL/Redis)— and platform work on Kubernetes, Ansible, GitHub Actions and Terraform on Azure.
AI offensive security came through the academic route: my master's thesis on adversarial campaigns against models, RAG systems and agents is the origin of NORN, an LLM red-teaming CLI framework with its taxonomy mapped to OWASP Top 10 for LLM, MITRE ATLAS and NIST AI RMF.
Everything I build ends up on GitHub: NORN and OSINT-OA are open source —sole developer on all three— and NAM was my final degree project. The thesis behind NORN is published, with its attack taxonomy, the campaigns and the metrics. I write code that ships and break code that should not.
CLI red-teaming framework for LLM applications. Runs structured adversarial campaigns against models, RAG systems and agents using a three-layer attack taxonomy, then produces scored reports with verified metrics for reliable, reproducible LLM security audits.
OSINT Agentic Operations — multi-agent OSINT platform that automates open-source investigations and IOC (indicator of compromise) extraction, orchestrating specialised agents across each phase of the intelligence cycle.
Network Analysis Module — my final degree project (2020): a multithreaded C packet sniffer (pcap with BPF filters) that samples 15 traffic features, sends them over UDP and classifies them in real time with a Random Forest.
// NO TRANSMISSIONS YET — CHECK BACK SOON
./contact --open-channel
Hiring for cloud/DevOps, AI offensive security or full stack — or got a project in mind? Drop me a line and we will take it from there.