Pablo García Ruiz logo
Back to blog
2 min read

What's Next: Vision Engineering at Indra Group

My current role as a Senior Vision Engineer at Indra Group, building AI-powered vision systems for defense and aerospace, and how the research years led here.

CareerComputer VisionDefense

Since December 2025 I’ve been a Senior Vision Engineer at Indra Group, back in Córdoba, designing and developing computer vision solutions for defense and aerospace applications. It’s the role that, in hindsight, the previous few years were quietly building toward.

Same disclaimer as always with defense work: I can talk about the shape of what I do, not the specifics of any one system. So consider this less “here’s the project” and more “here’s what the job actually is.”

From markers to mission-critical

A Ph.D. spent on camera pose estimation and fiducial markers turns out to translate surprisingly directly into “AI-powered vision systems for mission-critical environments”: the math doesn’t change just because the stakes did. What’s different is the environment: research code has to convince a reviewer and reproduce a result; this has to run reliably in the kind of setting where “it mostly works” isn’t a sentence anyone wants to hear.

Day to day, that means image processing and software engineering work sitting closer to systems engineering than to a research pipeline: less “can this be done at all,” more “can this be trusted every single time.”

Cameras, real products

A good chunk of the work is integrating industrial cameras, Keyence, IDS, Hikrobot, among others, into products that actually ship, rather than into a one-off research rig. On top of that hardware layer, I build vision checking systems: automated inspection products that catch what a manual check would miss. Some of that is for other clients’ projects, some of it is for defense, and same disclaimer as above applies to the latter: I naturally can’t say much about it.

Where vision engineering work sits in the stack A four-layer stack, drawn bottom to top. Industrial cameras from vendors such as Keyence, IDS and Hikrobot sit at the base as real hardware rather than a one-off research rig. Above them, an integration layer presents one interface over cameras that each have their own. Above that, vision checking systems perform automated inspection that catches what a manual check would miss. At the top is the product that ships to a client, which has to keep working quietly for years. A note beside the stack contrasts research code, which has to convince a reviewer and reproduce a result, with this work, where the question is whether it can be trusted every single time. No specific system is shown, because that part is confidential. The shape of the work, not the systemsDefence work is confidential; the stack it sits in isn't Productwhat actually ships, and has to keep working for years Vision checking systemsautomated inspection that catches what a manual check misses Integration layerone interface over cameras that each have their own Industrial camerasKeyence, IDS, Hikrobot, among others what changes Research code has to convince a reviewerand reproduce a result. This has to run reliably where “it mostlyworks” isn't a sentence anyone wants tohear. The maths doesn't change because the stakesdid. The environment does. Layers, not systems: the specifics of any one build aren't mine to publish.
Layers, not systems. Where the work sits, and what changes coming from a research pipeline.

Focus areas

Computer VisionMachine LearningCamera IntegrationIndustrial InspectionDefense & Aerospace

Tech stack

The general-purpose computer vision toolkit, applied in a much less forgiving setting:

C++PythonOpenCVCMakeGit

Why I like it

Vision engineering in this space sits exactly at the intersection I’ve always liked best: real computer vision problems, applied to something that actually matters operationally, with none of the “solve it once for a paper and move on” pressure that academic research runs on. The bar for a system like this is that it keeps working, quietly, for years, which is a genuinely different and satisfying kind of hard.

This is very much a current chapter, not a finished one. I expect this post to look understated in a year or two once I can say more about what’s actually been built.

Older postWhat I Can Say About My Time at ALTEN & AirbusNewer postFirst Steps Into BoundingBox.store