Computer Vision Engineer

We are seeking a hands-on Computer Vision Engineer to design, develop, and deploy production-ready AI solutions for image and video analytics. This role is ideal for someone who has built Computer Vision systems from the ground up and has experience with object detection, segmentation, OCR, image processing, and deep learning model deployment. The ideal candidate combines strong technical expertise with a passion for solving complex business problems through Computer Vision and Machine Learning.Key Responsibilities:Design, develop, and deploy end-to-end Computer Vision solutions from concept through production across image and video analytics use cases.Build and optimize computer vision pipelines for object detection, image segmentation, image classification, OCR, and document processing applications.Develop image processing workflows to improve image quality, enhance feature extraction, and optimize model performance across varied operating conditions.Evaluate, benchmark, and select Computer Vision architectures, including CNN-based and Transformer-based approaches, balancing accuracy, latency, scalability, and business requirements.Train, fine-tune, and optimize deep learning models using frameworks such as PyTorch and TensorFlow, leveraging transfer learning and custom model development techniques.Work closely with camera systems, imaging hardware, sensors, and edge devices to ensure successful deployment in real-world environments.Develop solutions capable of handling challenging image conditions, including low-light environments, variable lighting, motion blur, and image quality limitations.Define success metrics, analyze model performance, troubleshoot prediction issues, and continuously refine models using production feedback.Build and maintain data ingestion, annotation, training, evaluation, and deployment pipelines supporting rapid experimentation and production-scale implementation.Partner with software engineering, MLOps, and data engineering teams to deploy Computer Vision solutions into production environments.Required Qualifications:Experience4+ years of hands-on experience building and deploying Computer Vision and Machine Learning solutions.Demonstrated experience developing Computer Vision systems from the ground up, including data collection, annotation, model development, evaluation, deployment, and ongoing optimization.Proven experience deploying Computer Vision models into production environments and supporting operational performance.Experience developing solutions involving image analytics, video analytics, OCR, document processing, object detection, and image segmentation.Technical SkillsStrong expertise in modern Computer Vision techniques, including:Object Detection (YOLO, Faster R-CNN, SSD, DETR, or similar)Image Segmentation (U-Net, Mask R-CNN, SAM, or similar)OCR and document understanding pipelinesImage classification and feature extractionImage enhancement and image quality optimizationAdvanced Python programming skills for machine learning, computer vision, and image processing.Hands-on experience with PyTorch and/or TensorFlow.Strong understanding of image acquisition concepts, including:Camera hardwareImaging sensorsLens configurationsLighting environmentsHardware-aware Computer Vision design considerationsExperience developing Computer Vision solutions for environments with challenging image quality characteristics such as low-light conditions, glare, shadows, or inconsistent lighting.Experience optimizing and deploying models for edge and embedded environments while balancing performance, accuracy, and resource constraints.Preferred QualificationsExperience with Vision Transformers (ViTs), multimodal AI, and foundation vision models.Experience deploying optimized models using ONNX, TensorRT, quantization, pruning, or similar techniques.Experience with MLOps, model monitoring, experiment tracking, and lifecycle management.Experience working with large-scale image, video, camera, IoT, or sensor-based datasets.Experience in manufacturing, industrial inspection, surveillance, robotics, autonomous systems, healthcare imaging, or similar Computer Vision-heavy domains.