CV/ML Camera Test Engineer

The role

This person will measure how camera and optics choices affect AI model performance. They will design and run controlled experiments in lab and field setups to provide data for camera decisions.

What you will do

• Form testable hypotheses and design controlled experiments.
• Execute experiments comparing sensors, lenses, ISP settings, IR illumination, focus and window conditions.
• Build and maintain lab and outdoor test setups.
• Run field data-collection campaigns across sites, times of day, lighting and weather.
• Run captured video through existing CV/ML models and evaluation tools.
• Script captures, camera settings, data pipelines and analysis in Python and shell on embedded Linux devices.
• Isolate the cause of performance changes using statistical analysis and write reports.
• Support camera validation through EVT, DVT and PVT.

Required qualifications

• Bachelor's Degree in Electrical Engineering, Computer Engineering, Physics, Mechanical Engineering, Computer Science, or equivalent.
• 2+ years of experience in hardware test, validation or experimental work.
• Strong Linux command line proficiency, including SSH, logs, file and process management and shell scripting on embedded devices.
• Proficient in Python for scripting, data processing and analysis.
• A scientific, first-principles mindset.
• Hands-on with test setups and lab equipment.
• Comfortable doing outdoor field work, including at night and in bad weather.
• Strong grounding in statistics and experimental design.
• Exceptional organization and communication skills (both written and oral).

Nice to have

• Experience with cameras, image sensors, lenses or image-quality testing (MTF, SNR, low light, IR).
• Exposure to computer vision tools (OpenCV) or ML evaluation metrics such as precision and recall.
• Experience with video tooling such as FFmpeg, GStreamer or V4L2.
• Experience with thermal chambers, reliability or production test.
• Background in physics, optics or a research lab environment.
• Imatest or equivalent image-quality tools

About the company

Specter builds video sensors with state-of-the-art AI agents to automate the physical world. They are a small, fast growing team with founders from Anduril, Tesla, Uber, and the U.S. Special Forces.