AI Vision Engineer
AI Vision Engineer
Onsite, West
This position is responsible for designing, developing, fine-tuning, and optimizing deep learning models for quality inspection applications using 3D and wearable sensors. You will contribute to the development of advanced AI algorithms for sensing methodologies, object detection, recognition, segmentation, pose estimation, and human activity recognition across multiple modalities.
Key Responsibilities
- Design, develop, and optimize deep learning models to process and analyze sensor data from various modalities for quality inspection
- Apply deep learning techniques for human activity recognition across video and other modalities
- Evaluate and calibrate various sensors to ensure accurate data collection for training
- Pre-process and prepare image and sensor data for effective model training
- Validate algorithm performance on real-world datasets
- Document technical reports, program codes, and set-up manuals
Requirements
- Master's or Ph.D. degree in relevant engineering discipline with over 5 years of industry experience
- Familiarity with object detection, recognition, and segmentation frameworks
- Experience with human detection and human activity recognition models
- Experience with 3D sensor data from head-mounted cameras is a strong advantage
- Proficiency in data preprocessing and augmentation techniques
- Working knowledge of sensor methodologies
- Proven experience deploying deep learning models in real-world applications
- Patents, publications, specialist certifications, or awards in multimodal processing will be an added advantage
AI Vision Engineer
Onsite, West
This position is responsible for designing, developing, fine-tuning, and optimizing deep learning models for quality inspection applications using 3D and wearable sensors. You will contribute to the development of advanced AI algorithms for sensing methodologies, object detection, recognition, segmentation, pose estimation, and human activity recognition across multiple modalities.
Key Responsibilities
- Design, develop, and optimize deep learning models to process and analyze sensor data from various modalities for quality inspection
- Apply deep learning techniques for human activity recognition across video and other modalities
- Evaluate and calibrate various sensors to ensure accurate data collection for training
- Pre-process and prepare image and sensor data for effective model training
- Validate algorithm performance on real-world datasets
- Document technical reports, program codes, and set-up manuals
Requirements
- Master's or Ph.D. degree in relevant engineering discipline with over 5 years of industry experience
- Familiarity with object detection, recognition, and segmentation frameworks
- Experience with human detection and human activity recognition models
- Experience with 3D sensor data from head-mounted cameras is a strong advantage
- Proficiency in data preprocessing and augmentation techniques
- Working knowledge of sensor methodologies
- Proven experience deploying deep learning models in real-world applications
- Patents, publications, specialist certifications, or awards in multimodal processing will be an added advantage