Edge Performance Engineer - AI

Job Description

<p><b>Edge Performance Engineer - AI</b></p><p><b>Location:</b> Remote - Canada or Greater Toronto Area</p><p><br></p><p>A leading innovator in edge-based AI solutions is seeking a highly skilled Edge Performance Engineer to join their growing team. This cutting-edge role is at the intersection of hardware and AI, focusing on the optimization of GPU-accelerated vision pipelines running at the edge. This is a rare opportunity to influence the design and deployment of real-time computer vision systems across industrial and automation environments, with the support of a well-funded and visionary organization.</p><p><br></p><p>In this position, you'll take full ownership of the edge system performance lifecycle, from profiling and model optimization to system integration and observability. You'll work cross-functionally with machine learning, DevOps, and cloud engineering teams to ensure consistent, high-throughput inference at the edge. The ideal candidate thrives in resource-constrained environments and enjoys solving complex system-level challenges involving hardware acceleration, system bottlenecks, and runtime tuning.</p><p><br></p><p><b>Key Responsibilities</b></p><ul><li>Optimize performance of GPU-accelerated computer vision pipelines on edge hardware (e.g., NVIDIA Jetson, x86/ARM systems).</li><li>Improve throughput and reduce latency through advanced model optimization techniques (e.g., quantization, TensorRT, ONNX Runtime).</li><li>Profile and resolve system-level constraints across CPU, GPU, memory, storage, and network layers.</li><li>Collaborate with machine learning teams to deploy robust models that meet real-world resource constraints.</li><li>Integrate edge systems with observability and orchestration frameworks to ensure maintainability and scale.</li><li>Develop dashboards and tools to monitor edge performance KPIs like frame rate, latency, uptime, and resource usage.</li><li>Participate in root cause investigations for performance-related incidents on production systems.</li><li>Provide technical input on system design and hardware selection for new edge deployments.</li></ul><p><br></p><p><b>What You'll Bring</b></p><ul><li>5+ years of experience in software engineering with a focus on high-performance or real-time systems.</li><li>Strong background in GPU-accelerated development using CUDA, TensorRT, cuDNN, or equivalent vendor tools.</li><li>Proficiency in Python and at least one systems language such as C++ or Rust.</li><li>Proven experience in deploying and optimizing deep learning inference pipelines in production environments.</li><li>Advanced Linux skills and comfort using observability tools (e.g., perf, strace, eBPF).</li><li>Experience working with Docker and CI/CD workflows targeting edge devices.</li><li>Deep debugging capabilities across application, system, and hardware levels.</li></ul><p><b>Preferred Qualifications</b></p><ul><li>Background in edge AI, robotics, or industrial automation applications.</li><li>Familiarity with video processing frameworks (e.g., GStreamer).</li><li>Understanding of edge-specific challenges such as thermal throttling, intermittent connectivity, and limited bandwidth.</li><li>Exposure to Kubernetes or other edge orchestration frameworks.</li></ul><p><br></p><p><b>Why Join</b></p><ul><li>Work at the forefront of AI and computer vision innovation.</li><li>Solve tangible, high-impact problems in real-world deployments.</li><li>Join a mission-driven team with strong technical leadership and cross-functional collaboration.</li><li>Enjoy a flexible, remote-first work culture with top-tier talent across Canada and beyond.</li></ul><p><br></p><p><b>About Blue Signal:</b> </p><p>Blue Signal is an award-winning, executive search firm specializing in various specialties. Our recruiters have a proven track record of placing top-tier talent across industry verticals, with deep expertise in numerous professional services. Learn more at <b>bit.ly/46Gs4yS</b></p>