Deep Learning Engineer on Vision-based Autonomous Driving
The Computer Vision Center (CVC) is a non-profit research center established in 1995 by the Generalitat de Catalunya and the Universitat Autònoma de Barcelona (UAB). Its mission is to carry out cutting-edge research that has the highest international impact in the field of computer vision. It also promotes the transference of knowledge to industry and society.
One of the fields in which CVC works is vision-based autonomous driving enabled by deep learning. A current bottleneck is the relative low availability of annotated data to train artificial drivers based on deep learning. Thus, a line of work at CVC is driving based on imitation learning, i.e., training a vision-based “sensorimotor” model which does not depend on human annotation.
In this context, the project “Imitation Learning with Temporal Information”, led by Dr. Antonio M. López, studies how to include temporal information into an imitation learning paradigm for vision-based autonomous driving, with the goal of outperforming single-frame models. Accordingly, we look for a deep learning engineer specialized in the topics described below.
The candidate is intended to work 6 months starting during July-August 2022, further extensions are not guaranteed. However, please, do not understand this position as an internship. We are neither looking for undergrad nor for master students.
- Training and testing deep models using the pytorch framework and the CARLA simulator, as well as collaborating with other members of Dr. López’s team for improving the internal vision-based autonomous driving stack of the team.
- More than 2-year experience training and testing sensorimotor models for autonomous driving using pytorch and CARLA simulator.
- Strong experience training and testing transformer models for autonomous driving tasks, it would be specially appreciated if transformers were applied to sensorimotor driving models.
Requirements (Highly valuable):
- Being first author of papers on the above-mentioned topics (sensorimotor models for autonomous driving), published in international reputed conferences and/or journals.
- Having a very recent PhD or being in the last year of the PhD, focusing on the above-mentioned topics (sensorimotor models for autonomous driving).
- Start date: during July-August 2022.
- 6 months contract, full time (37,5h/week).
- Where: partially online partially in the CVC building, proportion to be negotiated.
- Salary: to be negotiated.
Application and criteria:
- Applicants must submit their curriculum vitae through CVC online form in this link https://www9.cvc.uab.es/work-with-us/, indicating offer code 20220613_ADAS
- Pre-selection: determination of compliance with the “must” requirements of the offer.
- Selection: assessment of the preselected candidates by scoring based on objective criteria (includes to consider the “highly valuable” requirements).
- Final decision: in case of finding the suitable person, the election will be formally communicated to him/her.
Application deadline: June 20,2022 23:59h.