ML Engineer
株式会社SUBARU
-
Tokyo
-
Over 10,000
-
Company Homepage
Job Summary
Utilize ML algorithms for object detection, road environment recognition, vehicle control, etc., and be responsible for modeling, learning, evaluation, and development. Utilize Python, C/C++, TensorFlow, etc., to optimize for edge devices and include extensive experience in function optimization and product orientation.Company Info
SUBARU is a car manufacturer that develops, manufactures, and sells automobiles. We aim to achieve carbon neutrality by 2050 and contribute to the progress of environmental activities, such as reducing the environmental burden of the main plant in northern Japan. Environmental management specialists are responsible for promoting environmental management, promoting the activities of the provincial environmental activities, and reducing the environmental burden of the main plant in northern Japan.Duties
As an ML engineer, you will be responsible for utilizing TensorFlow for object detection, road environment recognition, depth/motion estimation, vehicle control, etc., and be responsible for modeling, learning, evaluation, and development of the model. Additionally, you will be involved in the development of major development tasks such as Segmentation, 3D Vehicle Detection, VRU Detection, Debris Detection, General Object Detection, stereo/mono depth estimation, optical flow estimation, object tracking, path prediction, etc. You will use Python and C/C++ as development languages, and utilize TensorFlow as an OS for Windows and Linux, as well as Docker and GCP, to apply the latest technology and contribute to the safety improvement of autonomous vehicles.
Login to see all information about offers.
By registering with LabBase Plus you...

You can select from our vast stock of job offers.
- Can view all curation offers.
- Receive notifications of new offers added to curations.
- Possibly be scouted by corporations.
- Search for companies with unique technologies.
- Search for job offers in areas like inorganic chemistry material science.
Registration takes roughly 2 minutes