Principal Vision Developer

Description

• Build visual servoing systems for robot guidance and manipulation tasks
• Implement intelligent camera placement strategies to optimize coverage and minimize blind spots
• Integrate with access control systems for enhanced security monitoring
• Establish development standards for vision system deployment in nuclear environments
• Deploy vision models on edge devices, cloud infrastructure, and hybrid architecture
• Design detection pipelines that process video streams from multiple cameras simultaneously
• Integrate computer vision systems with Nuclear OS platform for seamless data flow and automated reporting
• Create facial recognition systems for access control and personnel tracking (where permitted)
• Develop automated inspection systems using AI and computer vision to verify construction quality and detect deviations
• Create truck and material arrival detection using camera-based AI at jobsite entrance gates
• Develop material classification algorithms that automatically identify installed components and materials from construction site images
• Develop visual comparison tools that overlay as-built conditions against design models to identify discrepancies
• Build camera management systems for configuration, monitoring, and maintenance of distributed camera networks
• Integrate vision systems with robotic inspection and quality control platforms
• Create visual SLAM systems for autonomous robot navigation in construction sites
• Build defect detection systems for automated quality inspection of welds, concrete pours, and structural installations
• Connect to IoT camera networks and drone feeds for real-time image acquisition
• Develop computer vision systems for robotic perception and autonomous navigation
• Implement transfer learning to adapt pre-trained models for nuclear construction-specific applications
• Build real-time video analytics systems that analyze camera feeds and drone imagery to detect construction issues, missing components, and deviations from design
• Optimize models for real-time inference on edge devices and GPU-accelerated servers
• Develop bandwidth optimization for efficient video streaming from large camera networks
• Implement worker tracking systems using camera-based detection for safety monitoring and emergency response
• Develop custom datasets from drone imagery, site cameras, and inspection photos with proper labeling and annotation
• Design and deploy multi-camera networks across construction sites for comprehensive visual coverage
• Implement photogrammetry pipelines for 3D reconstruction from drone and camera imagery
• Build optical character recognition (OCR) systems for automated document processing and equipment labeling
• Develop multi-camera synchronization for stereo vision and 360-degree coverage
• Integrate AI-enabled cameras into IoT sensor networks for real-time data collection and analysis
• Provide expert guidance on computer vision architecture, camera systems, algorithms, and best practices
• Develop appearance-based search for security and incident investigation across multiple camera feeds
• Drive innovation in automated construction monitoring and intelligent inspection systems
• Implement 3D reconstruction from image sequences and point clouds for digital twin development
• Create ensemble models that combine multiple vision techniques for robust performance
• Create camera health monitoring systems to detect and alert on camera failures or degraded performance
• Build automated progress assessment systems using computer vision to track work package completion
• Create automated alert systems that log safety violations and notify supervisors immediately when non-compliance is detected
• Design and develop AI-powered computer vision systems for automated construction progress monitoring, comparing current site images to BIM models to determine completion percentages
• Build APIs and microservices for vision system integration with other Nuclear OS modules
• Create surveillance video analysis systems to detect and track work packages' components automatically
• Mentor junior developers on machine learning, computer vision, and AI techniques
• Implement data pipelines for image ingestion, preprocessing, inference, and result storage
• Implement camera calibration systems for accurate geometric measurements and 3D reconstruction
• Build perimeter monitoring systems that detect unauthorized personnel or equipment breaches during critical operations like heavy lifts
• Build convolutional neural network-based detection systems for automated identification and classification
• Develop hazard detection models that identify unsafe conditions, obstructions, or potential safety risks in construction zones
• Implement continuous learning pipelines that improve model accuracy over time with new data
• Lead cross-functional teams involving data scientists, software engineers, network engineers, and domain experts
• Create computer vision algorithms for anomaly detection, defect identification, and automated image analysis from drone and camera feeds
• Create visualization dashboards showing real-time progress metrics, safety alerts, and quality issues
• Build tailgating detection systems that identify when multiple people enter on a single badge swipe
• Develop infrared and thermal imaging analysis for equipment monitoring and anomaly detection
• Train deep learning models (CNNs, transformers, YOLO, R-CNN) for object detection, segmentation, and classification in construction environments
• Implement vehicle and individual tracking across facility camera networks for security analysis
• Develop AI safety enforcement systems that analyze camera feeds in real-time to detect PPE compliance (helmets, vests, safety glasses)
• Evaluate emerging vision technologies including foundation models, vision transformers, and multimodal AI
• Implement activity recognition models (using YOLO, CNNs) to monitor construction activities and assess task completion times
• Design isolated security networks for camera systems in sensitive areas
• Represent TNC in industry forums on AI and computer vision applications
• Integrate various camera types including fixed surveillance cameras, PTZ cameras, thermal/infrared cameras, and mobile drone cameras
• Develop 3D pose estimation for robotic pick-and-place operations

Requirements

• Ph.D. in Computer Vision, Machine Learning, or related field
• Understanding of construction processes, quality control, and safety requirements
• Understanding of nuclear facility operations and safety protocols (preferred)
• Certifications in AI/ML (AWS ML Specialty, Google ML Engineer, etc.)
• Familiarity with camera mounting, positioning, and field-of-view calculations
• Excellent problem-solving abilities with creative approach to vision challenges
• Familiarity with real-time operating systems and embedded vision
• Knowledge of image processing techniques (filtering, segmentation, morphological operations)
• Familiarity with industrial inspection and automated monitoring systems
• 5+ years in a senior or lead role with demonstrated technical leadership
• Knowledge of data pipelines, ETL processes, and data versioning (DVC)
• Contributions to open-source computer vision projects
• Deep understanding of classical CV techniques (edge detection, feature extraction, optical flow, SLAM)
• Understanding of camera calibration, lens distortion correction, and geometric transformations
• Proficiency in video analytics and real-time processing
• Experience with video management systems (VMS) and network video recorders (NVR)
• Knowledge of security systems and surveillance best practices
• Knowledge of lighting design for optimal camera performance
• Project management experience delivering production vision systems
• Knowledge of BIM models, CAD data, and 3D visualization
• Expert programming skills in Python (primary) and C++ (for performance-critical code)
• Knowledge of camera protocols (ONVIF, RTSP, HTTP streaming, GigE Vision)
• Understanding of edge computing and model optimization (TensorRT, ONNX, quantization)
• Experience with model training, hyperparameter tuning, and optimization
• Proficiency in GPU programming (CUDA, cuDNN) for accelerated inference
• Publications in top-tier computer vision conferences (CVPR, ICCV, ECCV)
• Expert knowledge of deep learning frameworks (PyTorch, TensorFlow, Keras)
• Strong experience with camera integration, configuration, and management
• Attention to detail for accuracy-critical applications
• Experience in industrial, construction, or manufacturing applications preferred
• Understanding of network bandwidth requirements and optimization for video streaming
• Experience with large-scale image datasets and data annotation tools (Labelbox, CVAT, Label Studio)
• Proficiency in multi-camera synchronization and calibration
• Strong experience with CNNs, vision transformers, and modern architectures (ResNet, YOLO, Mask R-CNN, ViT)
• Proficiency in object detection, semantic segmentation, and instance segmentation
• Knowledge of containerization (Docker, Kubernetes) for model deployment
• Familiarity with cloud platforms (AWS SageMaker, Azure ML, Google Cloud AI)
• Understanding of REST APIs, microservices, and distributed systems
• Familiarity with streaming video processing and real-time analytics
• Background in robotics, autonomous systems, or industrial automation
• Strong communication skills to explain complex AI concepts to diverse stakeholders
• Understanding of data augmentation, regularization, and model evaluation techniques
• 12+ years of experience in computer vision, machine learning, or AI development
• Experience with various camera types (IP cameras, thermal cameras, PTZ cameras, industrial cameras)
• Experience with video surveillance systems and security analytics
• Experience with MLOps tools (MLflow, Weights & Biases, TensorBoard)
• Experience in nuclear, energy, or highly regulated industries
• Experience with multi-camera systems and camera networks
• Ability to work collaboratively across engineering, operations, security, and safety teams
• Bachelor's degree in Computer Science, Electrical Engineering, Computer Engineering, or related field (Master's or Ph.D. preferred)
• Knowledge of transfer learning, fine-tuning, and domain adaptation
• Experience with regulatory compliance and documentation requirements
• Proficiency in database systems for image metadata and results storage
• Knowledge of video compression standards (H.264, H.265, MJPEG)
• Understanding of camera specifications (resolution, frame rate, dynamic range, sensor types)
• Experience with 3D computer vision (stereo vision, structure from motion, photogrammetry)
• Expert proficiency in computer vision libraries (OpenCV, scikit-image, PIL/Pillow)
• Knowledge of 3D sensors (LiDAR, depth cameras, structured light)

Benefits

• Generous vacation policy, plus holidays
• Competitive compensation packages
• Medical, dental, vision plans
• 401k with company match

Training + Development

Interview process

Visa Sponsorship

Security clearance