At Marble, we believe a future where unmanned electric aircraft are flying 24/7, moving goods and sensors at no environmental and monetary cost, is inevitable and will be transformational.
We are a technology company bringing together top European talent to accelerate that event, by building the required technology for an industry that needs it right now: NGOs and small countries trying to protect their waters
Over the past 4 years, as a scrappy bootstrapped team we have developed a complete end-to-end solution that includes vehicle, ground infrastructure, and data management software, winning our first contracts with a less-than-perfect product, and deploying it in four countries, flying over 1,000km and detecting more than 200 illegal vessels.
We now are at a turning point: over the next 12 months we will complete a full redesign of the system, and compete for our first large deployment contracts.
If you are passionate about the problems we are solving, and want to join an early stage company where you will have the opportunity to have a large impact and ownership, come join us build the future of maritime protection and UAVs.
What you’ll do
Design, develop and maintain computer vision models for Marble’s maritime monitoring applications (e.g. boat detection and identification)
Design and maintain the hardware (computing, sensor and optics) to run the CV algorithm at the edge, on the aircraft
Work directly with customers (e.g. coast guards, NGOs, etc.)
Work in close relationship with aircraft engineering and operations teams to reduce pilot/co-pilot workload in flight
Support demonstrations and deployment with customers as needed, including travel
Required skills
2/3 years experience designing, developing and operating computer vision models
Experience with neural networks and YoloV5
Experience selecting and assembling hardware components for image collection and processing on the edge.
Comfortable working with uncertainty, under time pressure, with limited supervision and as part of a team.
Bachelors / Masters in a relevant field
