Real-Time Computer Vision Architect

What you'll do

• Translate high-level product goals into detailed system, module, and component requirements including firmware and OS constraints.
• Develop and optimize computer vision perception algorithms for performance, power, and memory on embedded platforms.
• Optimize ISP pipelines for tasks such as noise reduction, color correction, and dynamic range enhancement.
• Evaluate sensing trade-offs across cameras, depth sensors, and IMUs in collaboration with hardware and optical teams.
• Debug and optimize system performance at the firmware and OS levels to align hardware capabilities with algorithmic needs.
• Communicate technical trade-offs and requirements to cross-functional partners ranging from firmware engineers to feature teams.
• Bridge the gap between high-level algorithm design and low-level system optimization under tight power and latency constraints.

What we're looking for

• Bachelor's degree in Computer Science, Electrical Engineering, or a related field.
• Minimum of 10 years of relevant experience in the field.
• Proven track record in developing and improving CV perception algorithms and ISP pipelines.
• Experience optimizing computer vision algorithms for performance, power, and memory on embedded platforms.
• Strong understanding of perception sensing technologies including color/monochrome cameras, depth sensors, and IMUs.
• Expertise in at least one computer vision area such as SLAM, tracking, classification, or scene understanding.
• Ability to translate ambiguous product goals into detailed feature-level architectures and system requirements (preferred).
• Experience with modern techniques like vision transformers, foundation models, and vision-language models (preferred).