Get to know our Team:
The team has as a goal to automate as much as possible the map making process, leveraging artificial intelligence techniques for that. The envisioned end-result based on shared effort with other geo teams is the best SE-Asia map in the world to be used on all Grab products. It is a highly skilled team, containing machine learning engineers working side-by-side with Java developers, database developers or site reliability engineers. The will to help others and also continuously grow, the desire to deliver high standard, scalable and state of the art software are among this team’s defining traits. We also support the development of innovative, highly scalable, models through deep research and advanced analysis so that we make our products intelligent and delight our customers.
Get to know the Role:
- Work on improving the OpenStreetMap and enhancing it with automatic detections using artificial intelligence techniques applied on images and GPS points.
- Design and develop innovative AI architectures to address the emerging demands of computer vision and machine learning algorithms
- Use best practices to deliver high quality code and ensure the quality of the code for the whole project
- Implement unit, functional and performance tests
- Write and maintain technical documentation relevant to the project
- Participate in planning and estimation of effort to implement, test and maintain features
- Participate in code and design reviews to maintain high development standards
- Leading a group of people - when required - guiding them towards goals achievements
The must haves:
- A solid understanding and experience with Deep Learning, in particular with design, training, evaluation and optimization of convolutional neural net (CNN) architectures in the context of object detection, segmentation, scene classification, object tracking, OCR, etc.
- Self-motivated learner who keeps himself up-to-date with the current state of computer vision and deep learning techniques/architectures.
- Able to communicate well in English both verbally and in written communication, as well as convey data insights and results with effective visualisations.
- Experience with Python and some of the following libraries: Tensorflow or Caffe or PyTorch or Fast.ai; NumPy; OpenCV; scikit-learn;
- Understanding of machine learning methods for classification, regression and clustering.
- Strong skills in deadline management and ability to work in a team environment
- Fast learner and adaptable to changing environment
- Analytics and design skills
- Experience with CNN architectures in the context of object detection, segmentation, scene classification, object tracking and/or OCR
- Understanding of image processing technologies based on innovative computer vision (ex: projective geometry, stereovision and 3D reconstruction) would be a high plus.
- Experience in curating, manipulating and analysing large geographical or spatio-temporal datasets.
- Experience in designing, deploying or maintaining ML systems in production
- Familiarity with NoSQL frameworks or search engine / indexing frameworks like ElasticSearch
- Familiarity with GIS frameworks and/or databases (e.g. PostGIS).
- Familiarity with Azure cloud platform
