AI & Platform Engineer — LLM apps · agents · distributed systems
Salvador
F. Criado
I build production AI end to end — agents, RAG and real-time voice, plus the GPU inference underneath. Eight years shipping distributed systems on AWS and Azure that stay up.
remote worldwide · utc+1 · open to permanent senior / staff roles
8+ yrssystems in production
<2.0svoice loop, end to end
100k+users on platforms i've run
3clouds: aws · azure · on-prem
What I do — AI engineering and platform work
LLM applications & agents
Hybrid RAG with reranking on Qdrant, agentic flows with tool calling against a live CRM, a Spanish voice loop under 2 s. In production, on client hardware.
Serving & evaluation
vLLM and NVIDIA Triton, quantisation with LLM Compressor, GuideLLM benchmarks, Langfuse tracing and golden-set regression gates.
The platform underneath
AWS to certified DevOps Pro level, Terraform, Kubernetes, event-driven pipelines and time-series at volume. Eight years of it.
Selected work — production LLM and cloud systems
On-prem voice agents for an enterprise contact centre
Agentic flows, RAG on Qdrant and a streaming voice loop under 2 s — on the client's own GPU, data never leaves the network.
2025–26Real-time telemetry platform for 1,000+ industrial sensors
Event-driven ingestion on AWS Lambda and IoT Core, time-series validation and routing, critical-event detection and alerting, plus an LLM layer answering questions over the live data. Took ownership after the team went from 20+ engineers to a handful.
2024–25AWS → Azure migration of a 100k-user e-learning platform
Multi-tenant Moodle/Laravel platform moving onto AKS: Terraform, Azure DevOps pipelines, tenant-by-tenant cutover. In progress.
2026 — now
Writing
Field notes
The half of your GenAI system nobody put on call
Nobody's RAG system breaks — it quietly stops being right. The jobs nobody wrote down, three mechanisms that make them safe, and what to put on a dashboard.
New notes land in the RSS feed. No newsletter, no signup. Hiring? mail@salvadorfcriado.com.
About — AI engineer in Granada, Spain, remote
Hands-on engineer in Granada, Spain — remote worldwide. I started close to the metal, on PCBs and firmware, and worked up through distributed systems to platforms carrying a hundred thousand users. Applied AI is the newest layer on that stack, not a replacement for it: I still reach for Terraform and a profiler before I reach for a bigger model.
What I'm looking for: a permanent, fully remote senior or staff role — applied AI on top of real platform work, or platform work that is about to need it. Hands-on by preference, happy to lead. EU national, no sponsorship needed in the EU, available worldwide within a workable timezone overlap.
- Now
- Independent consultant · AI & platform engineering — Sep 2025 to present. On-prem LLM voice, applied-AI bootstraps, and an AWS → Azure platform migration.
- Before
- Lead Software Engineer, industrial IoT data platform (2024–25) · Software Engineer, consulting — IaC, e-learning at scale, nuclear-plant alert filtering (2022–24) · Full-stack cloud & IoT (2018–22) · Postgraduate researcher, UPM (2017–18).
- Education
- MSc Electronic Systems, Universidad Politécnica de Madrid · BEng Telecommunications (Electronics), Universidad de Granada.
- Certifications
- AWS Certified DevOps Engineer – Professional · Agentic AI (DeepLearning.AI) · Certified ScrumMaster.
- Languages
- Spanish (native) · English (professional) · French (basic).
- Stack
- Python · TypeScript / Node.js · vLLM · Triton · Qdrant · Langfuse · AWS · Azure · Terraform · Kubernetes · Docker · PostgreSQL · MQTT.