Senior Computer Vision Engineer

About the role

You will architect and own the end-to-end design of cloud and edge computer vision systems that power real-time wildfire detection and situational awareness for outdoor environments. In this hands-on technical leadership role, you will define the roadmap for AI models and inference pipelines spanning edge devices and the cloud. You will advance core capabilities such as wildfire smoke detection, vegetation understanding, and asset recognition while enabling spatial reasoning across complex scenes. You will directly influence how ultra-high-definition camera networks and AI deliver actionable intelligence to first responders and critical infrastructure operators. Your work will ensure that models are not only accurate but also efficient, reliable, and deployable under real-world constraints. You will collaborate closely with hardware, software, and data teams to align vision algorithms with platform requirements and customer needs. This position offers the opportunity to tackle a growing global challenge by turning cutting-edge research into resilient, field-deployed safety systems.

Key facts

What you'll do

• Design and implement cloud and edge AI architectures that support real-time computer vision workloads for wildfire detection and outdoor monitoring.
• Develop computer vision models focused on wildfire smoke detection, vegetation detection and classification, asset detection such as power lines and utility poles, scene understanding, and semantic segmentation.
• Build lightweight detection, segmentation, classification, and temporal reasoning models that meet real-time inference constraints on resource-limited hardware.
• Port and optimize deep learning models across ARM64, CUDA, TensorRT, ONNX, and NVIDIA Jetson platforms to maximize compatibility and performance.
• Build and optimize inference pipelines for RGB, NIR, PTZ, and multi-camera systems in both cloud and edge contexts.
• Develop hybrid edge-cloud AI workflows that balance latency, bandwidth, and compute efficiency while maintaining detection accuracy.
• Improve inference latency, throughput, memory usage, and power efficiency to meet operational requirements in field deployments.
• Lead model compression efforts including quantization, pruning, and knowledge distillation to reduce model size and computational cost.
• Integrate models with downstream data sources and coordinate with satellite imagery and other sensing modalities to enrich situational awareness.
• Define and drive measurable improvements in detection precision, recall, and false-alarm rates across diverse environmental conditions.
• Collaborate with data engineering and infrastructure teams to ensure scalable data ingestion, labeling, and training workflows.
• Partner with product and field teams to align model capabilities with customer needs and regulatory requirements.
• Own the end-to-end lifecycle of computer vision models from experimentation and validation to deployment and monitoring in production.
• Mentor and guide junior engineers by providing technical direction, code reviews, and best practices for model development and deployment.

Requirements

• Hold a Bachelor's, Master's, or PhD degree in Computer Science, Electrical Engineering, or a closely related technical field.
• Demonstrate extensive experience with computer vision, including image classification, object detection, segmentation, and model optimization.
• Show strong proficiency in deep learning frameworks such as PyTorch or TensorFlow and experience deploying models to edge platforms.
• Bring hands-on experience with model optimization techniques including quantization, pruning, and knowledge distillation.
• Have a solid understanding of inference on ARM64, CUDA, TensorRT, ONNX, and NVIDIA Jetson ecosystems.
• Demonstrate expertise in building and optimizing inference pipelines for multi-camera and multi-sensor systems.
• Possess strong programming skills in Python and experience with C++ for performance-critical components.
• Exhibit a proven track record of turning research into production-grade computer vision systems that operate at scale.

Nice to have

Experience with outdoor and long-range imagery, thermal or NIR cameras, and wildfire or safety-critical applications.

Practical notes

This role is full-time and based in San Francisco, California. Applicants must be authorized to work in the United States without sponsorship now or at the time of hire. The listed compensation range is not available in the source information. Please note that hours, travel, visa, or deadlines are not specified in the provided source.