AI/ML Engineer

Overview Quarterhill is seeking a talented and versatile AI Engineer to join our dynamic team in Saskatoon, SK. We are looking for candidates with a proven track record in developing scalable infrastructure for image and video analysis, deploying deep learning models, and building robust computer vision pipelines. This role integrates expertise in AI engineering with real-time analytics and edge computing while working on intelligent systems that process live video feeds and multi-sensor data at the edge. Responsibilities Develop and integrate AI inference pipelines using tools such as NVIDIA DeepStream, TensorRT, and CUDA, focused on real-time performance and optimization. Create pipeline components for video decoding, object tracking, metadata streaming, and stream multiplexing. Build logic for multi-stage inference flows, such as detection followed by classification or feature extraction, while managing frame correlation. Engage in data governance, keeping track of the lineage of data sets and how they relate to the models that utilize them. Integrate real-time communication and data exchange between applications and services using lightweight messaging protocols, such as ZeroMQ (ZMQ). Optimize inference performance and resource utilization across Jetson Xavier/Orin or similar NVIDIA edge devices. Collaborate with SMEs and domain engineers to align pipeline outputs with project requirements and evaluation metrics. Write maintainable, modular, and performance-sensitive code capable of running reliably in embedded environments. Develop custom plugins or components to support specialized AI inference workflows or sensor integrations. This list of responsibilities might not cover everything you'll end up doing. Qualifications Qualifications Bachelor’s or Master’s degree in Electrical Engineering, Computer Engineering or a related engineering field. 3+ years of experience in AI/ML development, with a focus on computer vision and real-time systems. Strong proficiency in Python, especially in building data pipelines using NumPy, OpenCV, and common AI libraries. Experience working with NVIDIA DeepStream SDK for stream-based AI inference and real-time model deployment. Experience with TensorRT, CUDA, and model optimization techniques for edge deployment. Understanding of structured inference outputs, frame-level metadata tagging, and pipeline synchronization. Familiarity with ONNX model conversion and deployment workflows in DeepStream or TensorRT environments. Understanding of INT8/FP16 precision optimization and calibration techniques for edge inference performance. Preferred Skills Working knowledge of video processing tools, and understanding of when to use DeepStream as a higher-performance alternative. Experience with inter-process communication frameworks, especially in low-latency applications. Benefits We offer a Total Rewards plan designed with you and your family’s health and wellness in mind that includes: Paid days off (i.e. vacation, sick days, bereavement leave) Health and Dental plans Retirement plans Employee and Family Assistance Program (EFAP) Employee referral program We welcome applicants from all backgrounds, regardless of race, color, religion, sex, veteran status, sexual orientation, gender identity, national origin, age, or disability or any other protected characteristics in accordance with applicable federal, state/provincial, and local laws. We're committed to creating a workplace where everyone feels valued and respected. We appreciate all responses and will acknowledge only those being considered for an interview. We respectfully request no calls or unsolicited resumes from Agencies.