Airobotics is a leading company specializing in the development and manufacturing of autonomous drone systems. Its solutions combine hardware, software, and AI-driven technologies to support complex, large-scale operations. Airobotics works primarily with defense industries, such as military and law enforcement agencies worldwide.The company is part of Ondas Holdings and operates as a wholly owned subsidiary.
We are seeking for AI Data Scientist to join our team, with a strong focus on computer vision applications. The ideal candidate will have experience in AI vision tasks such as object detection, SLAM, tracking, and real-time image processing, while also being comfortable applying AI techniques to non-vision data when needed.
Our AI vision models are designed to run efficiently on edge devices such as NVIDIA Jetson, Raspberry Pi, and similar platforms, with opportunities to contribute to broader AI research and applications across the company.
What We Offer
- Opportunity to work on cutting-edge AI vision and robotics challenges.
- Collaborative and innovative work environment.
- Professional growth in a cross-disciplinary AI and robotics setting.
- Computer Vision & AI Model Development
- Design, train, and optimize AI vision models for object detection, recognition, tracking, and SLAM.
- Develop robust pipelines for real-time video and image analysis.
- Deploy and optimize models for edge environments (Jetson, Raspberry Pi, etc.) as well as cloud systems.
- Research & Innovation
- Stay updated with state-of-the-art methods in computer vision, deep learning, and robotics-related AI.
- Experiment with novel techniques to improve the accuracy, efficiency, and robustness of vision models.
- Cross-Disciplinary AI Applications
- Occasionally design and implement AI models for non-vision data (e.g., sensor data, tabular data, time-series, NLP-based tasks).
- Integrate multimodal AI approaches combining vision and non-vision data for enhanced decision-making.
- Data Management & Evaluation
- Collect, curate, and annotate datasets for AI model training and validation.
- Implement data augmentation, preprocessing, and synthetic data generation pipelines.
- Define and monitor key performance metrics for deployed AI systems.
Collaboration
- Work closely with engineers from different disciplines to integrate AI models into production systems.
- Document models, pipelines, and findings for reproducibility and knowledge sharing.
Required Qualifications
- Strong background in deep learning frameworks (e.g., PyTorch, TensorFlow).
- Proven hands-on experience with object detection and tracking models (e.g., YOLO-based frameworks).
- Experience in SLAM and real-time computer vision applications.
- Expertise in building end-to-end AI pipelines, including preprocessing, training, validation, and deployment.
- Experience with real-time inference on edge and GPU platforms.
- Solid understanding of machine learning concepts, probability, and optimization.
- Proficiency in Python and scientific computing libraries (e.g., NumPy, OpenCV, SciPy, scikit-learn).
- Experience in training, fine-tuning, quantizing, and deploying models on edge devices (e.g., Jetson, Raspberry Pi, etc.) and GPUs.
Preferred Qualifications
- Knowledge of 3D vision techniques (stereo vision, depth sensing, LiDAR fusion).
- Exposure to non-vision AI applications such as NLP or time-series forecasting.
- Strong problem-solving skills and ability to work in fast-paced R&D environments.
Skills Required
- Strong background in deep learning frameworks (e.g., PyTorch, TensorFlow).
- Proven hands-on experience with object detection and tracking models (e.g., YOLO-based frameworks).
- Experience in SLAM and real-time computer vision applications.
- Expertise in building end-to-end AI pipelines, including preprocessing, training, validation, and deployment.
- Experience with real-time inference on edge and GPU platforms.
- Solid understanding of machine learning concepts, probability, and optimization.
- Proficiency in Python and scientific computing libraries (e.g., NumPy, OpenCV, SciPy, scikit-learn).
- Experience in training, fine-tuning, quantizing, and deploying models on edge devices (e.g., Jetson, Raspberry Pi) and GPUs.
- Knowledge of 3D vision techniques (stereo vision, depth sensing, LiDAR fusion).
- Exposure to non-vision AI applications such as NLP or time-series forecasting.
- Strong problem-solving skills and ability to work in fast-paced R&D environments.
What We Do
Airobotics Ltd. is an Israeli manufacturer and operator of Unmanned Aircraft systems deployed as mission-critical strategic aerial infrastructure for government and commercial entities all over the world. Airobotics provides trusted autonomous drones used for Safe & Smart Cities, Defense, Homeland Security, industrial projects and facilities, performing various automated aerial missions 24/7 with no human intervention. Founded in 2014, Airobotics combines expertise in aerospace hardware design, robust electronic systems, cutting-edge software engineering, and years of experience in commercial drone operations across a variety of environments. This blend of experience and expertise has enabled Airobotics to create the world's most reliable and effective autonomous unmanned systems and to implement them as mission-critical infrastructures to address the needs of the most complex environments in the world. Airobotics systems enable end-users to operate drones in real-time anytime, anywhere for aerial data capture and analysis, aerial delivery, and interception. Together with customized data analysis platforms, Airobotics systems enable faster, more effective, and more efficient operations and fully informed critical decision-making. The Airobotics Optimus is a fully automated drone system, comprising a drone, an airbase, swappable payloads and designated software. The system has a wide range of regulatory certifications and is the first of its kind in the global market to include a robotic arm swapping payloads and batteries for 24/7 continuous, unmanned aerial missions. The Airobotics Iron-Drone System is a fully automated interceptor drone launched from a designated pod, flying autonomously, and intercepting malicious drones.
