Location: Córdoba, Argentina

Location: Córdoba, Argentina Remote: Yes, remote only Willing to relocate: No Technologies: TypeScript, React, Next.js, Node, GraphQL with Apollo, Playwright, SQLite, Postgres, LLM agents, MCP servers, RAG, promptfoo evals, OpenTelemetry Résumé/CV: https://portfolio-aguirre-alexis.vercel.app GitHub: https://github.com/ale-aguirre Email: [email protected] Full-stack dev, 5+ years, last year spent building LLM products rather than demos. I have a document comparison SaaS running in production at an Argentine auto parts manufacturer, 72 employees, in a domain audited against IATF 16949 and ISO 9001. Two people there use it for their actual work. The interesting part is not the LLM call, it is the semantic reclassification I run after it, because the model kept flagging paraphrases as real differences. I also run an autonomous job search agent on my own search. The useful thing it taught me was that my own verifier was lying. It counted a URL redirect as a successful application, and one integration had been failing at zero percent for months while the aggregate sat at seventy eight. A job posting with hidden instructions once got that same agent to write ten years of Kubernetes into my CV. The system prompt did not stop it, a deterministic validator did. I published that as intent-gate on npm. Yesterday I shipped a PR and two issues to an open source AI SDLC project, one of them about an agent being able to write the field that marks its own check as platform verified. Open to full-time or contract.