Optics & Camera Engineering

**Company Background
**Specter's mission is to help automate the physical world.

Today, we build video sensors with state-of-the-art AI agents that answer any question, anywhere in their environments. Our systems can automatically detect and reason about any physical activity captured on camera, from security incidents (e.g. perimeter intrusion, theft, LPR), to safety monitoring (e.g. PPE detection, injured people), to operational efficiency (e.g. material tracking, congestion monitoring). We offer both long range wireless (1km range) and wired sensor variants to suit any deployment.

Our co-founders Xerxes and Philip are passionate about empowering our partners in the fast approaching world of physical AI and robotics. We are a small, fast growing team who hail from Anduril, Tesla, Uber, and the U.S. Special Forces.

The RoleSpecter is hiring an Optics & Camera Engineering Lead to own camera performance across our product portfolio. This individual will own the imaging stack end to end: sensor and lens selection, optical requirements tied to CV/ML and customer outcomes, vendor and JDM programs, test campaigns and results analysis, and high volume production. This individual will collaborate with systems, software, CV/ML, electrical, mechanical, manufacturing, supply chain and test teams to deliver performant, scalable and validated camera + optical systems to the field.

The role spans the full stack. One day you'll be benchmarking sensors and lenses for a new product. Next, you'll work with our CV/ML team to translate detection, recognition and LPR performance at range into pixel density, MTF and low-light targets, or review athermal lens designs, define a slant-edge MTF test across temperature, or analyze a wiper endurance run. You'll work with systems, software, electrical, mechanical, manufacturing and supply chain, and lead technical engagements with tier-one optics and sensor suppliers.

Responsibilities:

Select sensors and lenses

• Evaluate and select image sensors for each product, comparing low-light performance (SNR1s, QE at 850/940 nm), pixel size, resolution, frame rate, HDR, supply life and cost.

• Select off-the-shelf lenses or specify custom designs matched to each sensor: FOV, F-number, MTF across the field, NIR correction, distortion, relative illumination and athermal behavior.

• Evaluate and select the ISP architecture (on-sensor, companion ASIC/FPGA or SoC ISP), weighing image quality, latency, power, cost and supply, and drive ISP tuning and pipeline development for day and NIR night modes.

• Benchmark sensor and lens candidates side by side in the lab and the field, and keep a qualified roster of sensors, lenses and IR-cut filters ready for new programs.