Machine Learning Deployment Engineer [ C++ ]

Please read carefully the qualifications and responsibilities and include relevant skills in your CV

Oreyeon is a startup company and part of the NVIDIA inception program, providing AI solutions for
airports focusing on safety and automation of operations. Oreyeon's goal is to re-imagine airport safety
by implementing proactive features, eliminating human error and reducing costs by using cutting-edge

We are looking for a full-time Machine Learning Deployment Engineer [ C++ ]. You must be passionate
about creating new technologies, ready to grasp knowledge fast and solve complex problems in AI and
Computer Vision.

Education: Bachelor’s in Computer Engineering/Computer Science (similar technical field of study or
equivalent practical experience). Preferably Masters Degree.

Experience: 1-2 years

Key Qualifications:
● Strong C++ development skills under Linux OS (Ubuntu)
● Solid knowledge and proven experience in Python
● Practical experience with deploying Deep Learning models (compression, optimization,
engines, etc.)
● Practical experience with Linux Embedded systems
● Hands-on experience with TensorFlow, Keras and OpenCV
● Experience with CUDA & CUDNN
● Experience with NVIDIA TensorRT
● Skilled at software development
● Excellent analytical, development and debugging skills
● Worked on implementing Computer Vision and Deep Learning applications (Segmentation,
Object Detection, Classification)
● Worked on robotics related projects
● Ability to research, implement and prototype new algorithms in an agile environment
● Familiarity with Amazon Web Services
● Ability to work efficiently remotely
● Ability to work with new hardware SDKs such as cameras and sensors

Bonus Qualification:

● Experience in neural network quantization, compression, pruning algorithms


The responsibilities expected from the person filling the role include but are not limited to:

● Deploy AI models on embedded systems
● Design, implement and troubleshoot an end-to-end Computer Vision pipeline
● Optimize real-time application performance on limited memory and power modules
● Implement parallel computing algorithms
● Run and evaluate alpha testing on prediction pipelines applications
● Compress and optimize ML models
● Communicate clearly with ML team to synchronize project timeline
● Use project management tools (Jira, Trello, etc.)
● Document efficiently all tasks
● On-going research on latest technologies and innovation in the field
Soft Skills Required:
● Writing & communicating in English easily
● Document solutions and explanations clearly
● Communicate with peers professionally
● Report to team meeting on a daily basis

Apply on LinkedIn or by sending your CV and a cover letter

Esta oferta de emprego já não aceita candidaturas, pelo que não é possível apresentar a forma de responder. Sugerimos que faça uma Pesquisa de emprego a fim de encontrar uma oferta disponível.

Mais sobre esta oferta

Esta oferta de emprego foi inserida pela empresa. em Quinta, 17 Dezembro, 2020 - 17:54. A resposta a este anúncio de emprego tem como data limite: Sábado, 16 Janeiro, 2021.

Outras ofertas