Computer Vision Engineer

Get AI-powered advice on this job and more exclusive features. You thrive at the intersection of computer vision, AI, and impactful real-world use cases. Whether it’s building smart surveillance systems or solving complex video analytics problems, you're always seeking elegant, scalable solutions. You bring hands‐on experience with detection, recognition, and tracking, and you get excited about tools like OpenCV, DeepStream, and YOLO. Your Role as a Zenika Consultant As a consultant, you’ll work on strategic client engagements, including high‐impact government contracts. You will develop robust computer vision pipelines and lead innovation in edge AI solutions. You’ll work alongside client teams to: Design, develop, and deploy computer vision models and algorithms for real-time video stream analysis. Implement methods for real‐time object detection, tracking, and pose estimation of people and assets within a facility environment. Develop logic for anomaly detection related to people safety and security, such as unauthorized access, unsafe behavior, or unusual crowd movements. Process and integrate large datasets from video streams and other sensors into a digital twin framework. Build the core temporal and spatial inference engine, translating 2D video data into accurate 3D representations and events for the digital twin. Collaborate with the UI/UX team to define and deliver the data structure required for their digital twin visualization interface. Analyze historical data to identify trends, improve model accuracy, and support predictive modeling capabilities. Write clean, well-documented, and efficient code in Python. Participate in code reviews, contribute to architectural discussions, and mentor junior team members if required. What You Bring Must‐Haves: 3+ years of professional experience in software development, with a strong focus on computer vision and video analytics. Proven experience working on large-scale data processing and real-time systems. Experience in the full machine learning lifecycle, from data acquisition and annotation to model training, evaluation, and deployment. Computer Vision & AI/ML: Deep understanding and hands‐on experience with modern computer vision models for object detection (e.g., YOLO, Mask R‐CNN, EfficientDet ), tracking, and segmentation. AI/ML Frameworks: Strong command of at least one major deep learning framework ( PyTorch or TensorFlow ). Core Libraries: Extensive experience with fundamental libraries like OpenCV, pandas, NumPy, and Matplotlib . Computer Graphics & 3D: Solid foundation in computer graphics, including a practical understanding of: Scene Graphs: Experience in organizing and manipulating complex 3D scenes. 3D Geometry: Knowledge of 3D vectors, matrices, and coordinate systems. 2D/3D Projection & Transformations: The ability to translate between 2D camera images and the 3D world space. Data Handling: Experience processing and managing large-scale, high-velocity datasets from multiple sources. GPU & Parallel Computing: Experience with CUDA programming and parallel computing for optimizing GPU usage. Nice‐to‐Haves: Digital Twin & Simulation: Prior experience with digital twin platforms, real-time simulation, or 3D visualization engines (e.g., Unity, Unreal Engine, NVIDIA Omniverse). Knowledge of virtual simulation architectures and entity component systems. Sensor Fusion: Experience integrating and processing data from multiple sensor types beyond cameras (e.g., LiDAR, IoT sensors). 3D Reconstruction: Experience with physical‐to-digital workflows for creating digital twin assets, particularly the handling and processing of point clouds, photogrammetry, and 3D reconstruction. Generative AI & Synthetic Data: Familiarity with generative AI for creating synthetic data to augment training sets. Cloud & MLOps: Experience with cloud platforms ( AWS, Azure, GCP ) for model deployment, and a solid understanding of MLOps practices, including containerization (Docker) and orchestration (Kubernetes). Programming Languages: Knowledge of C++is a plus, particularly for performance-critical components. Real-Time Data: Experience with real-time messaging and streaming protocols. Knowledge of distributed computing for inference runtimes. Specialized Knowledge: A background or strong interest in industrial safety, security protocols, or smart facility management, particularly in public safety applications of AI. Communication: Excellent communication skills and a collaborative mindset, comfortable working with cross-functional teams. Founded by developer Carl Azoury, Zenika is a consultancy built around community, transparency, and craftsmanship. We are passionate technophiles advising clients with deep expertise in open‐source tech and modern solutions. Work with a global client base across 11 locations, benefiting from over 28,000 Zenika‐led training sessions. Partner with tech giants like Google Cloud and Scrum.org, and engage in research, open-source contributions, and conferences outside client projects. Participate in Zenika tech conferences (TechnoZaures) to learn, share, and grow together. 20 days of annual leave + up to 5 LEAP (Learning, Education, Advancement, Progress) days. Dedicated Learning & Development (L&D) budget to support your growth. Flexible benefits package to cater to your well‐being and lifestyle needs. Comprehensive international medical insurance package. Ready to code your story with us? Apply NOWSeniority level Mid‐Senior level Employment type Full‐time Job function Information Technology Industries IT Services and IT Consulting Referrals increase your chances of interviewing at Zenika Singapore by 2x. Get notified about new Computer Vision Engineer jobs in Singapore, Singapore . Queenstown, Central Singapore Community Development Council, Singapore 8 months ago. #J-18808-Ljbffr