Who We Are
Kimedes AI is a deep-tech climate technology company founded in December 2024 in Arenys de Munt, on the Maresme coast of Catalonia, Spain. Europe loses around 25% of its treated drinking water before it reaches the tap—largely due to leaks in buried, decades-old pipelines. Excavating to find them is slow, expensive, and often guesswork.
We took a different path: instead of deploying hardware underground, we built a data cube over the network—combining satellite and environmental data from multiple independent sources, stacked over time—read by our AI engine to detect the subtle signature of buried leaks. No single data source suffices; making them agree is most of the work. From here, we’re building tools to act on these insights. Our flagship platform, Syracusa, turns detections into inspection plans and regulatory audits that municipalities can execute the same week.
We’re four founders with paying production customers, recognized by the European Commission with GovTech4All Silver 2026, backed by the European Space Agency (ESA), selected in ACCIÓ Top 25, and granted access to supercomputing at the Barcelona Supercomputing Center. Scientifically, we collaborate with CTTC and IEEC.
The Role—Straightforward
Think. This role is about thinking.
We have a problem—and we need you to think deeply about it. We believe the solution lies in a deep learning model, and we want you to lead it: own the model and the development of supporting tools.
Not just maintain them—but design them, deploy them to production, and define their maintenance workflows. This is the fun part: building Kimedes, not just keeping it running.
We have an ESA-funded R&D project with contractual deliverables and deadlines, and a second national 3-year project that extends it. The AI component of both is yours. You’ll start from a blank slate, with access to supercomputing, remote sensing physicists at your fingertips, and a first deliverable in five months.
Your architectural decisions will become documents reviewed by the European Space Agency. Your model’s predictions will trigger municipal crews drilling into streets. Both carry real consequences.
We’re a small team, so we offer great freedom—and expect autonomy and problem-solving skills. That’s exactly what we provide: space to grow professionally, with the freedom to implement things your way.
What You’ll Do
Design
Architect a model that ingests multi-source, multi-temporal satellite and environmental data over the same territory and outputs leak probability—spatial and temporal fusion, handling irregular acquisition schedules.
Contribute to AI design decisions, grounding them in physical reality: adapting loss functions or transformer-based architectures, refining variables, or designing data preprocessing pipelines to improve model metrics.
Help design and build the ecosystem we’re creating around the core model.
Document architectural decisions—including discarded alternatives and rationale. This isn’t bureaucracy: it’s what external technical reviewers assess.
Train
Build the training pipeline and architecture tournament, with a written promotion rule: a configuration enters only if it significantly beats the classical baseline and doesn’t degrade calibration.
Solve severe class imbalance: the events we seek are rare, and models tend to learn to say “no.” Calibrate probabilities and report metrics adjusted to natural prevalence.
Scale training on the Barcelona Supercomputing Center, using distributed training and ablation studies to quantify each data source’s contribution.
Deploy to Production
Package the inference engine as a service with an API, so the platform can consume it and a municipal technician receives a usable map the same day.
Support field validation: compare model predictions with field findings, understand failure modes, and recalibrate. This is what separates a pretty model from one that works.
What We’re Looking For
Requirements
At least 4 years of experience training models used in production (notebooks don’t count).
Strong Python and PyTorch proficiency.
Experience designing architectures—not just using them—and ability to defend design choices and explain trade-offs.
Experience with spatio-temporal or multimodal data, and understanding why random splits are misleading when spatial correlation exists.
Deployed models in production—someone has acted on your predictions.
Working proficiency in English: deliverables go to ESA, scientific meetings are technical and conducted entirely in English.
Highly Valued
Remote sensing: radar, interferometry, coherence, optical multispectral.
GIS knowledge (PostGIS or similar).
HPC or distributed training experience.
Handling severe class imbalance and probability calibration.
Applied physics or modeling background (for physical consistency).
PhD. Not required, but especially well-suited for this role.
Not Required
Water sector experience—you’ll learn it in the first pilot.
Team management experience—this is an individual contributor role.
What We Value Most
We’re a small team that has come far through hard work. We seek proactive people who propose solutions to problems, aren’t shy to ask basic questions in meetings, and can’t sleep until they understand why a result came out a certain way. Curiosity about the physical reality of what we measure—and enthusiasm for testing unconventional ideas.
What We Offer
Your Time Is Yours
38.5-hour workweek (Spanish legal standard: 40 hours). We chose less—and wrote it into the contract.
Friday afternoons are 6.5 hours, uninterrupted. All of August is also 6.5 hours/day.
25 days of vacation + your birthday off.
Flexible start time between 8:00 and 10:00.
~1,686 productive hours/year vs. 1,800 in the collective agreement.
Hybrid Work—With Clear Rules
2 days in our office in Arenys de Munt, 3 days remote (from your agreed home address).
Up to 4 weeks/year may require full presence—only for objective reasons and with written notice. Four weeks is the ceiling.
Full home and office workstation provided and paid for by us. Remote work agreement in place from day one, with monthly compensation for internet and electricity.
No messages sent after 6:00 PM.
Your end time shifts with your start time—but our communications don’t. If something arises at 7:30 PM, it’s scheduled for the next morning. Not “you’re not obliged to reply”—it simply doesn’t get sent.
Tools & Science
MacBook and full workstation on day one.
Claude Pro for everyone: AI is part of how we work, not a rationed extra.
Direct access to supercomputing for real training—not shared GPUs.
You will publish. We collaborate with CTTC, IEEC, and BSC—and research that stays in a drawer is wasted research. Conferences are evaluated case-by-case, no annual quota: if it matters to where the company is going, you go and present.
How We Work Together
Periodic 1:1s with founders (who sit right next to you). Real input on company direction—strategy doesn’t trickle down at our size.
Monthly demo days, one offsite/year in Catalonia, team lunches on the first Friday of each quarter, and a year-end dinner.
What we won’t promise: foosball, offsites in Marrakech, or fluffy adjectives about passion and excellence. We’re a handful of people with satellites, real customers, and a serious problem.
Salary Range
€38,000 gross annually
Hiring Process
Four stages, completed in three weeks:
Initial call (30 min): We present the project; you share what you’re looking for.
Design discussion (90 min): We present the real problem and think through it together on a whiteboard. No right answer, no coding—just how you reason when the problem is unsolved. No 20-hour take-home tests.
Scientific conversation (60 min): With our research partners—you ask them questions too.
Final interview with founders (45 min), followed by an offer.
We respond to everyone—whether there’s a fit or not.
Where We Are
Arenys de Munt, Maresme—40 minutes along the coast from Barcelona. Mountains behind, sea in front, and a commute that doesn’t eat your life.
How to Apply
Write to us telling us about a model you built that you’re proud of—and what you’d do differently today. That tells us more than any cover letter.
At Kimedes, we select based on what you can do and how you think—not your gender, age, origin, orientation, or any other trait unrelated to the job. If you need accommodations during the process, let us know—we’ll adapt.
Data Controller: Kimedes Artificial Intelligence S.L., B75632604
Purpose: Manage this recruitment process. We’ll retain your data for 2 months after the process closes. You may exercise your rights of access, rectification, deletion, opposition, limitation, and data portability at
[email protected]. Full details: [Privacy Policy link]