Top Computer Vision Jobs in NYC, NY

Lead development of predictive maintenance systems using computer vision, integrating multiple data sources to optimize equipment life and availability.

Lead research, design, and production implementation of computer vision and ML solutions. Define architectures, run experiments, own model lifecycle (data, training, evaluation, deployment), optimize inference, set MLOps standards, mentor engineers, and collaborate with product and engineering teams to deliver production-quality CV features.

Design, implement, test, and maintain scalable C++ software for autonomous vehicle and perception systems. Work across full SDLC, support vehicle testing, simulation-based regression, data acquisition/analysis from remote vehicles, root-cause analysis, and mentor engineers while collaborating with ML researchers and cross-functional teams.

Design, develop, and maintain Java-based, cloud-native image-processing services on GCP. Build REST APIs, image pipelines, and AI-enabled capabilities (OCR, classification, redaction). Implement secure coding, IAM, CI/CD, infrastructure-as-code, and observability. Collaborate with DevOps, QA, product, and security stakeholders and support deployments and production troubleshooting.

Lead design and implementation of computer vision systems for mapping, localization, image analysis, and 3D reconstruction on construction site data. Develop and optimize SLAM/SfM/VIO, deep learning perception models, and multi-modal approaches. Prototype, test, oversee datasets and collaborate with platform engineers to productionize scalable, robust solutions.

Lead development of orthomosaic tile imagery products for FireSat and SBEM: design and implement scalable mosaicking, orthorectification, and radiometric normalization algorithms; write production-ready code; author technical and customer-facing documentation; validate scientific quality; engage stakeholders and act as product owner for SBEM granule product; collaborate with engineers and scientists.

Remote entry-level Computer Vision Engineer to fetch and preprocess unstructured data, build image/video pipelines with OpenCV/scikit-image/Pillow, and develop deep learning models (TensorFlow/PyTorch) including CNNs, RNNs and autoencoders for real-world applications. Work as an individual contributor on product development within a lean team and collaborate with data scientists.

Lead perception vision, strategy, and roadmap for AV perception. Drive advances in detection, classification, tracking, fusion, and prediction; design sensor suites; define KPIs; hire and manage engineering teams; coordinate cross-functional deployment and issue resolution to ensure robust commercial autonomy performance.

Lead UI/UX engineering for cloud-enabled AI/ML mission systems supporting maneuver, surveillance, and engagement. Design and prototype interfaces (computer vision, sensor fusion, dashboards), test and evaluate performance on operational datasets, analyze results, optimize for robustness and cyber resilience, troubleshoot deployed systems, produce technical documentation, and mentor team members while liaising with government stakeholders.

Lead the development of AI-driven OCR and Image Recognition solutions, focusing on innovation, strategy, and team management in the retail sector.