The successful candidate will be responsible for developing end-to-end perception pipelines, optimizing machine learning models for edge deployment, and ensuring reliable performance under challenging conditions such as occlusion, varying lighting, motion, environmental interference, and complex multi-object scenarios.
Key Responsibilities
- Design, develop, train, and optimize computer vision and machine learning models for object detection, classification, recognition, and tracking.
- Develop robust multi-object tracking and re-identification solutions capable of maintaining continuity through occlusions, rapid movement, environmental challenges, and sensor variations.
- Create object selection, prioritization, and decision-making algorithms for complex scenes containing multiple targets or points of interest.
- Optimize machine learning models for deployment on embedded and edge computing platforms, ensuring efficient operation within real-time processing and resource constraints.
- Define, monitor, and improve key performance indicators including detection accuracy, tracking stability, false alarm rates, response latency, and target reacquisition performance.
- Develop and maintain data collection, annotation, augmentation, and dataset management processes to support model development and continuous improvement.
- Build simulation, validation, and testing environments to evaluate algorithm performance across diverse operational scenarios.
- Design interfaces between perception components and downstream software systems, ensuring accurate transfer of object state information, confidence metrics, timestamps, and spatial data.
- Support system integration, verification, validation, and performance testing activities.
- Conduct root-cause investigations, performance analysis, and model tuning to address edge cases and challenging operating conditions.
- Research and evaluate emerging computer vision, machine learning, and artificial intelligence techniques to improve system capabilities.
- Produce technical documentation covering algorithms, model architecture, performance results, validation activities, limitations, and deployment strategies.
Requirements
- Strong proficiency in Python and C++ with extensive experience developing production-quality software applications.
- Deep knowledge of computer vision, machine learning, and deep learning methodologies.
- Hands-on experience with object detection, object classification, segmentation, and multi-object tracking algorithms.
- Strong experience with modern deep learning frameworks such as PyTorch, TensorFlow, or equivalent technologies.
- Experience optimizing and deploying machine learning models on embedded, edge, GPU-accelerated, FPGA-based, or specialized AI hardware platforms.
- Working knowledge of image processing techniques including image enhancement, denoising, stabilization, super-resolution, and feature extraction.
- Familiarity with multiple sensor technologies, including visible-light, thermal, infrared, and other imaging systems.
- Experience evaluating model performance using quantitative metrics and validation methodologies.
- Understanding of real-time perception systems and low-latency processing requirements.
- Experience with software development best practices, including version control, testing frameworks, continuous integration, and code reviews.
- Strong analytical, troubleshooting, and problem-solving capabilities.
- Ability to work independently while collaborating effectively within multidisciplinary engineering environments.
- Excellent written and verbal communication skills with the ability to explain complex technical concepts to both technical and non-technical stakeholders.
Qualifications
- Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Machine Learning, Electrical Engineering, Robotics, Data Science, or a related technical discipline.
- Minimum of 6 years of hands-on experience in computer vision, machine learning, artificial intelligence, or related fields.
- Demonstrated experience developing and deploying real-world perception systems for robotics, automation, intelligent devices, industrial systems, autonomous platforms, or similar technology domains.
- Strong understanding of end-to-end perception architectures, sensor integration, real-time data processing, and edge-computing environments.
- Experience with large-scale dataset development, annotation workflows, model training pipelines, and performance optimization.
- PhD in a relevant field is considered an advantage.
Preferred Experience
- Real-time object detection and tracking systems.
- Multisensor and sensor-fusion applications.
- Edge AI and embedded machine learning deployment.
- Robotics, automation, intelligent systems, or autonomous technologies.
- Performance optimization for low-latency and resource-constrained environments.
- Large-scale machine learning model development and operational deployment.
