I speak on making AI work in production — evals, observability, cost-efficient scale, and the agentic development practice behind it. Concrete, proof-first, no hype. Talks in English and Spanish; based in Madrid, remote-friendly.
SHORT
Pablo Albaladejo is a Senior AI Engineer at Aircall, where he makes AI work in production — predictable in quality and cost, on a platform handling more than a million calls a day. He created Kaiord, the open-source local-first training platform, written end to end by agents.
LONG
Pablo is a Senior AI Engineer (AWS, TypeScript) with 17+ years in software engineering. At Aircall he builds the AI behind call summarization — real-time transcription and LLM features on serverless microservices, on a platform handling over a million calls a day. His work is making that predictable in quality and in cost: evals as CI gates, traces on every call, and cost-efficient scale. On his own time he ships products written end to end by agents under spec-driven development and a zero-tolerance CI — including Kaiord, an open-source, local-first training platform with a TypeScript SDK, CLI, and MCP server.
He speaks to engineering audiences on treating evals as CI, tracing stochastic systems, and briefing agents with specs. AWS certified at Professional level; GitHub Certified: Agentic AI Developer. Based in Madrid, Spain.
01 25 or 45 min · talk
Why offline benchmarks lie, how to resample golden sets from production, and how to gate deploys on evals so model changes ship weekly instead of quarterly. Drawn from running LLM features on a platform handling 1M+ calls a day.
02 30 min · talk
How to brief AI agents so they ship production code: the spec format, the review loop, the CI that catches what the agent misses. What changes when the bottleneck moves from writing code to specifying it.
03 25 min · talk or workshop
Aggregate metrics hide the failure; the trace names it. Instrumenting retrieval, tool calls, and token flow so a regression bisects to a diff in minutes instead of a debugging séance.
04 25 min · talk
Search is no longer the only front door — increasingly, AI agents decide what to recommend. Generative Engine Optimization (GEO) is how you make your product legible to them. This talk covers the concrete surface area: llms.txt as a machine-readable map of your site, structured data and JSON-LD that state facts unambiguously, and the registries — like the official MCP registry — where agents actually look. I use a single-day GEO program I ran on Kaiord as the worked example: what shipped, what moved, and what didn't. You leave knowing which signals are worth the effort, which are cargo-cult, and how to instrument discoverability so you can tell the difference with data.
Every claim above is verifiable on these properties.
Conferences, internal engineering days, podcasts. I tailor the talk to your audience and bring the proof, not the hype.