About this role
Summary: The Senior Edge Computer Vision Engineer owns the performance and reliability of production computer vision pipelines on edge systems. This role involves optimizing real-time video processing for maritime safety, managing bottlenecks across hardware and software, and ensuring robust deployment of AI models on...
Orca AI builds AI-powered vision systems that enhance safety and decision-making for some of the world’s largest vessels. Our platform processes live multi-camera video to detect and track marine objects in real time, even in low visibility and congested waters. It's deployed on thousands of vessels and has processed hundreds of millions of nautical miles of real-world data.
This is a senior, systems-focused role. You'll own the performance and reliability of our production computer vision pipelines on the edge: define the optimization strategy, find the bottlenecks across the system, and ship improvements with a direct, measurable impact on safety. You'll work close to the hardware.
What you’ll do
- Build and optimize real-time computer vision pipelines running on edge systems processing liSenior Software Engineer, Computer Vision (Edge / Real Time)ve maritime video streams (e.g, NVIDIA Jetson, Triton Inference Server)
- Take models from research and turn them into production-ready, reliable components deployed on vessels
- Optimize model inference using techniques such as quantization, pruning, and graph-level optimization (e.g., TensorRT, ONNX Runtime)
- Profile and improve end-to-end system performance across: multi-camera video ingestion; preprocessing; inference; postprocessing
- Identify and resolve bottlenecks across CPU, GPU, memory, and pipeline coordination
- Make and justify tradeoffs between latency, accuracy, stability, and resource utilization
- Design and implement robust data and inference pipelines (video -> model -> actionable output for crew)
- Develop benchmarking and evaluation workflows to measure performance end-to-end and support release gating
- Build and improve observability tools and debugging workflows for production systems
- Define and maintain clear interfaces between research code and production systems
- Work closely with research and backend teams to integrate new models into production systems
- Continuously improve system efficiency and reliability under hardware and runtime constraints
- 5+ years building production systems, with at least 2 in computer vision or real-time video pipelines
- Hands-on experience working with computer vision or deep learning systems in production
- Strong C++ (modern C++, multi-threaded, real-time) and solid Python
- Experience working with edge or embedded systems (e.g., NVIDIA Jetson platforms or similar)
- Strong understanding of inference optimization (e.g., CUDA, TensorRT, ONNX, GStreamer/DeepStream) and system bottlenecks, including CPU, GPU, memory, and latency constraints
- Strong intuition for profiling-driven optimization and performance tuning
- Experience debugging complex systems and reasoning about behavior in real-world, noisy environments
Strong advantage
- Experience working with custom high-performance data or inference pipelines
- Familiarity with multi-sensor fusion (e.g., combining vision with radar or other signals)
- Experience deploying and maintaining ML models in production environments
- Experience with low-level optimization and/or C++ performance tuning
- Proven experience optimizing model inference (e.g., TensorRT, ONNX Runtime, quantization, pruning, or similar techniques)