Computer Vision / Machine Learning Engineer
Computer Vision / Machine Learning Engineer
As a computer vision / machine learning engineer at Arlo Technologies, you will design and develop algorithms, detection models, and software for advanced video and audio analytics features for Arlo’s Smart Home devices. This area comprises both deep learning and traditional machine learning or computer vision techniques and algorithms. Specific areas of interest include motion detection, object detection and tracking, action recognition and video understanding, facial and biometric recognition, reidentification, audio recognition, natural language, and others.
Required knowledge, skills and experience of the candidate
- Expertise in computer vision and machine learning.
- Working experience in software development in company or startup.
- Advance knowledge of TensorFlow, PyTorch, MXNet frameworks.
- Experience in using OpenCV.
- Familiarity with state of the art for computer vision. Strong knowledge of at least one of the following approaches: CNNs and deep learning, SVM, Bayesian Networks, boosting, feature based detection (SIFT/SURF family), object tracking, video analytics, audio analytics.
- Strong fluency in C++ and/or Python.
- Experience in using development tools such as GIT.
- Good verbal and written communication skills.
- Ability to work independently.
Your responsibilities will include
- Designing models for achieving specific video or audio analytic goals.
- Performing model training and optimization.
- Designing and implementing algorithms for performing a variety of computer vision or audio related tasks.
- Creating/modifying software and tools for implementing your algorithms and models on cloud infrastructure and edge devices.
- Working with data engineers to wrangle datasets to train and test your models.
- Working with a team of software and hardware engineers to deploy the software and tools that you have developed.
- Working with product marketing teams to help productize product features in a compelling fashion, understand customer feedback and define new iterations of product features.