Sr. Software Engineer, Embedded Vision Systems

Our vision at Vivid Machines is to revolutionize agricultural production to help solve food security globally. Our initial focus is on helping fruit and vegetable farmers improve the quality and quantity of produce they can generate on existing acreage while also improving sustainability. To do this, we are building cutting-edge technology, including real-time vision systems and state-of-the-art AI models, all while delivering a seamless experience to farmers.

As a Senior Engineer, you will have the opportunity to work on challenging problems throughout our software stack, designing and developing robust and scalable solutions across embedded systems, cloud, and mobile. You’ll be collaborating with our multidisciplinary team to create an amazing product and solve one of the world’s most important problems.

Do you love solving complex problems, and want to see your work applied in real life? We are looking for people who are self-directed and driven by a desire for excellence as much as by curiosity and a desire to learn by solving previously unsolvable problems.

Join our extraordinary team

We value excellence, integrity, curiosity, passion, open-mindedness, and decisive action. We iterate quickly, deliver with purpose, and work with people who bring their unique strengths to the team.

If you love supporting customers, the pace of a scaling startup, and want to make a global impact, we’d love to meet you.

How you’ll make an impact

Our cameras ride through orchards on farm vehicles, capturing multiple synchronized video streams, while geolocating and analyzing individual trees and fruit in real time. That happens on a single embedded compute module, in the field, with no operator, in the sun and the dust, on hardware we design ourselves. We are offline first, and a connection to the cloud is a bonus, not a dependency.

• Own the capture and inference pipeline. Multi-camera video from sensor to model to storage. No copies, no dropped frames, and it stays that way as resolution and model complexity go up.

• Make heavy vision models run in real time on hardware you can’t upgrade. Fixed power and thermal budget.

• Bring up cameras and sensors at the driver level.
• Turn sensor data into geometry. Fuse vision, position and motion into per-tree geolocation you can defend against surveyed ground truth.

• Make field problems reproducible at a desk. Replay of real scans, synthetic sources, on-device CI, regression tests against ground truth. Verify the fix before it ships.

• Identify problems before our customers do: frame drops, latency, thermal and power headroom, sensor health, storage. The camera must notice its own problems.

• Take our next generation platform from hardware definition to shipping product, help decide what that hardware should be.

• Ship to a remote fleet that’s online intermittently.

Whatwe’relooking for

We care much more about depth in the class of problem than about matching a tool list. If you have built real-time vision systems that had to work on hardware you couldn’t upgrade, you will recognize this work.

• Strong systems programming ability in a compiled language, such as C, C++, or rust, and real comfort at the boundary between application code, drivers and hardware.

• Experience building real-time streaming media or vision pipelines. Buffer management, latency and throughput, backpressure, zero-copy memory, and the discipline to profile instead of guess.

• Hands-on experience deploying vision models to edge devices.

• Experience with cameras and sensors at a low level. Image sensors, capture drivers, timing and synchronization, I2C/SPI/GPIO peripherals.

• Comfort with Linux as an embedded platform: kernel customization and debugging, containers, cross-compilation.

• Experience making a distributed or embedded system observable: metrics and logs from devices you can’t reach, dashboards and reports someone other than the author will use, and accuracy or quality tracked over time rather than measured once.

• Self-direction. This is a small, distributed team;
  the person in this rolewill often be the one who decides what “done” means.
  

Nice to have

• Streaming or event-based frameworks, such as ROS or gstreamer, including writing custom elements.

• Embedded vision processors and neural network acce lerators
  and corresponding profiling and performance optimization techniques.
• Kalman filtering, multi-object tracking, and geometric state estimation or photogrammetry.

• Telemetry and observability pipelines, time-series metrics, and building dashboards or automated reporting on top of them.

• Agriculture, robotics, autonomy, or any other domain where the physical world refuses to cooperate.

People from all backgrounds can succeed at Vivid Machines. We believe differences and diversity help build excellent businesses.

Why do you want to work at Vivid Machines?

• As an early employee of a VC-backed company, you will have the opportunity to help shape the company's vision,cultureand products,
• You can help build an amazing product in a company that plans to change the world,
• You will be offered competitive compensation,
• Competitive benefits package.
• Open, friendly, collaborative company culture,
• Company-sponsored team events and retreats,
• Free drinks and snacks.

Where to from here?

We want to ensureit’sa good fit on both sides, so you get a job you love, and we offer you a placeyou’reproud to work at.

Vivid Machines is an equal opportunity employer committed to providing a working environment that embraces and values inclusion and diversity.

#J-18808-Ljbffr