Mario Ruiz Sánchez
Senior Software Engineer (platforms, LLM, MCP)
[email protected] · https://marioruiz.net · LinkedIn · GitHub · RubyGems · SmartBot YouTube
Summary
Work at senior IC scope: I own SmartBot for 800+ employees across 30+ time zones. I build the platforms other engineers actually use — Slack, web, JSON API and MCP tooling (560k+ interactions). I take messy operational work and turn it into commands, dashboards, APIs and agent tools other people actually run.
Awarded the NetApp Public Cloud Excellence Award (Most Innovative Employee) in 2021, for SmartBot.
Outside work: a bilingual book of poems and music albums, published under a pen name in 2026.
How I work
I ship through agents (Cursor, Claude Code, Claude Desktop, and other MCP clients, plus an MCP server I built). I design, review, and operate; the implementation loop is part of the product. The same ANF analyzers are one structured payload for Slack, SmartBot Web, and IDE agents — not three separate tools.
Experience
Software Engineer — NetApp
Nov 2018 – presentNetApp · Reykjavík
- MCP + JSON API (May 2026). One structured surface for ANF analyzers so Slack, SmartBot Web, and IDE agents (Cursor, Claude Code, Claude Desktop) share the same payload.
- LLM in Slack. Team ChatGPT sessions with a team knowledge base as context; natural language for 50+ commands (ANF Sessions launch Aug 2025). 40k+ LLM session calls.
- SmartBot platform. Extensible Slack + web automation I designed and built. 250+ commands, 800+ employees, 150+ Slack channels, 30+ time zones. Commands cover general work such as team management, plus product commands. Channel-local rules so teams can automate daily work from desktop or mobile Slack. SmartBot put LLM tools in Slack for 800+ employees, cutting repetitive ops work and speeding how teams ship.
- Azure NetApp Files and Cloud Volumes Service. The same command and API-test pattern as Azure NetApp Files also runs for Cloud Volumes Service (CVS) on AWS and Google Cloud.
- Scheduled jobs, not only on-demand. A large share of volume is routines: region health, test-location analysis, and scheduled workflow triggers.
- SmartBot cleanup service. A SmartBot cleanup service people run in Slack — plus web UI, REST and dry-run — to delete stale Azure test resources. It contributed to $2M+ in cloud cost reduction.
- API tests from the spec. I built tools that generate API tests from the product OpenAPI/Swagger, so the suite stays in step with the spec instead of being written by hand.
- API tests / SmartBot Web. Own the test and operations stack: TypeSpec-aligned OpenAPI, change-impact detection, multi-region coverage. SmartBot Web from scratch (Oct 2025): basic tests, cleanup service, analytics, tutorials — so tests and cleanup do not depend on asking me in Slack.
- Unblock global teams on urgent incidents; mentor; review PRs. Record tutorials so the tools stay used.