This role requires strong expertise in computer vision, real-time systems, and search infrastructure, with a focus on turning visual data into actionable spatial intelligence.

• Design and implement algorithms for multi-camera object detection, classification, and persistent tracking.
• Build scene understanding modules to extract landmarks, spatial layout, and semantic context from image streams.
• Develop cross-camera fusion and localization methods for consistent identification and positioning of objects.
• Architect and deploy visual search systems using vector databases (e.g., OpenSearch, FAISS, Milvus) for image-based retrieval and matching.
• Design and implement re-ranking techniques to improve retrieval precision based on context, metadata, and scene cues.
• Create tools and metrics to evaluate retrieval quality, localization accuracy, and perception robustness.
• Collaborate across ML, backend, and infrastructure teams to ensure scalable, real-time deployment.
• Investigate system-level issues, drive debugging efforts, and improve model and system performance.
• Mentor junior engineers and contribute to long-term vision for perception, localization, and image retrieval.

• M.S. or Ph.D. in Computer Science, Robotics, Electrical Engineering, or a related field.
• 5+ years of industry experience in computer vision, image retrieval, or perception systems.
• Strong background in object detection, tracking, and scene understanding using multi-camera inputs.
• Deep understanding of vector-based retrieval systems and experience with OpenSearch, FAISS, or similar tools.
• Proficiency in Python or C++, with hands-on experience in PyTorch, TensorFlow, and OpenCV.
• Experience in building large-scale image retrieval pipelines, including feature extraction, indexing, and search optimization.
• Knowledge of multi-view geometry, and cross-camera identity association.
• Experience evaluating and tuning re-ranking strategies using contextual and multi-modal signals.
• Exposure to cloud-based deployment of search systems (e.g., OpenSearch cluster tuning, sharding, replication).
• Experience with edge deployment of perception pipelines (e.g., Jetson, Qualcomm).
• Publications or patents in the fields of visual search, localization, or multi-camera perception.

Metropolis Technologies is an equal opportunity employer. We make all hiring decisions based on merit, qualifications, and business needs, without regard to race, color, religion, sex (including gender identity, sexual orientation, or pregnancy), national origin, disability, veteran status, or any other protected characteristic under federal, state, or local law.