Collaborate with other members of the Perception team to develop algorithms that can enable the autonomous vehicle to better understand its environment.
Develop and maintain multi-modal, multi-view, multi-task end-to-end deep learning models that can help solve various perception objectives like object detection and tracking, and scene understanding.
Complete ownership of project from ideation, design, developing data requirements, model training, evaluation and deployment.
Research and prototype novel solutions which can help tackle the long-tail of real-world problems in challenging and diverse scenarios (e.g. on highway and local roads, extreme weather conditions, sensor failures, etc).
Ensure all model development keeps a real-time focus and operates efficiently in compute-constrained environments.
Rigorous approach to model development: running well-designed experiments, defining suitable training and validation datasets, and evaluating on the right metrics.
Required Skills:
MS or PhD in CS, EE, mathematics, statistics or related field.
1+ years of experience.
Expertise with Python, willingness to do some C++ development as needed.
Deep understanding of machine learning principles and methodologies.
Experience with implementing and maintaining deep learning pipelines.
Experience working on deep learning models in at least one deep learning framework (PyTorch, Tensorflow).
Preferred Skills:
Relevant industry experience (prior work on self-driving vehicles, autonomy, computer vision and/or robotics projects).
Past experiences in deep learning projects involving object detection, motion tracking or semantic segmentation.
In-depth understanding of cutting-edge deep learning techniques and architectures like transformers, CNNs.
Experience or familiarity with vision transformers is a plus.
Salary Range
$150,000 - $190,000 a year
Our compensations (cash and equity) are determined based on the position, your location, qualifications, and experience.
