Image Processing Engineer, Testing & Automation

About the company

Efference provides high-performance perception and compute infrastructure for training and deploying robot models in the cloud. Our vision is to make robotic deployments scalable with shared compute.

We approach the problem by owning the entire path from the image sensor to the datacenter GPU. We shrink the load at the sensor, fix the uplink so robot traffic is fast and reliable, and clock synchronize the system so observations arrive time-aligned, ready for inference.

About the role

You'll build the tools and test systems that let our imaging team measure changes quickly and trust the results. You'll combine camera testing with software development, turning image-quality experiments and field failures into repeatable checks across devices and software versions.

What you’ll do

• Build automated capture and analysis tools for RAW images, processed frames, video, and the metadata needed to reproduce each result.
• Develop controlled test setups for lighting, charts, motion, and camera configuration, working with algorithm engineers to define measurable acceptance criteria.
• Implement metrics for spatial detail, noise, exposure, color, dynamic range, and temporal artifacts; validate the metrics against known defects.
• Maintain versioned datasets and comparison reports that connect each capture to hardware revision, calibration, ISP settings, and firmware build.
• Integrate camera and image-processing tests into continuous integration, with useful failure artifacts and reliable handling of lab equipment and device resets.
• Reproduce imaging bugs, reduce them to test cases, and maintain regression coverage as algorithms and sensors change.

What we are looking for

• Strong Python skills and experience building maintainable test, data-processing, or automation software.
• Hands-on experience with cameras, image processing, or computer vision through industry, research, or substantial technical projects.
• Understanding of basic image-quality concepts and an ability to distinguish an algorithm defect from capture or measurement variation.
• Comfort with Linux, Git, automated tests, and organizing datasets so another engineer can reproduce an analysis.
• Attention to experimental detail and an ability to communicate failures with clear evidence and practical next steps.

Nice to Have

• Experience with OpenCV, NumPy, C++, image-quality measurement tools, or camera-control interfaces.
• Work on programmable lighting, motion stages, robotic test rigs, or hardware-in-the-loop automation.
• Experience with embedded camera platforms, containerized test runners, or large video regression datasets.