Contribute to Zoox's online mapping initiative by designing and integrating ML models to detect semantic map elements, critical for scaling autonomy in self-driving technology.
The Perception team at Zoox is fundamental to our autonomous vehicle technology, creating the understanding of the world for our self-driving robots. We enable safe and efficient navigation in complex environments through sophisticated detection, classification, and tracking systems.
As a software engineer on the perception mapping team, you will be a key contributor to Zoox’s online mapping initiative. You will design, train, validate, and integrate into the stack ML models that detect semantic map elements in the world. Your work will touch on all aspects of ML development, including data gathering, labeling, training, validation, and onboard integration. Your work will enable important milestones to scaling and autonomy capabilities and will be critical to the success of Zoox.
In this role, you will:
Curate, validate, and label datasets for model training and validation
Research, implement, and train ML models to perform semantic map element detection
Closely collaborate with validation teams to formulate and execute model validation pipelines
Integrate models into the greater onboard autonomy system within compute budgets
Be a technical leader on the team, maintaining coding and ML development best practices and contributing to architectural decisions
Qualifications:
MS or PhD or equivalent experience (5+ years) in Computer Science or related field
Experience in computer vision or robotics
Experience with training and deploying deep learning models
Experience with with Python libraries (pytorch, numpy)
Bonus Qualifications:
Experience with C++
Experience with CUDA and/or GPU programming
Experience with mapping related ML techniques
