Autonomous vehicles and LiDAR sensors in general are booming and play a key role in many industries.
Computer Vision community is actively doing R&D in this field, but there is a lack of tools and infrastructure now.
Entry barrier in this field is huge. Working with 3D point clouds is one of the main interests of Supervisely.
We have managed to create infrastructure for visualizing, operating and processing both separate point clouds
and point cloud episodes (including photo context).
We are in close cooperation with industry leaders in autonomous vehicles, agriculture and other domains
to build the best 3D point cloud infrastructure. Also our developments are shared
with the open-source ML community for free.
Our goal is to build the best tools for point clouds that will help engineers and data scientists to significantly speed up
development in this field.
You can think of Supervisely as an Operating System available via Web Browser to
help you solve Computer Vision tasks. The idea is to unify all the relevant tools within a single
Ecosystem of apps, tools, UI widgets and services
that may be needed to make the AI development process as smooth and fast as possible.
More concretely, Supervisely includes the following functionality:
Data labeling for images, videos, 3D point clouds and volumetric medical images (DICOM)
Data visualization and quality control
State-Of-The-Art Deep Learning models for segmentation, detection, classification and other tasks
Interactive tools for model performance analysis
Specialized Deep Learning models to speed up data labeling (aka AI-assisted labeling)
Synthetic data generation tools
Instruments to make it easier to collaborate for data scientists, data labelers, domain experts and software engineers
Implementing apps to cover basic data operations: data exploration, visualizations, import, export, converters between different formats, filtering, etc
Working with sensor fusion data: images, videos, pointclouds, GPS trajectories, radar, etc ...
Working with popular dataset formats, like Waymo, nuScenes, kitti and others
Adopting Supervisely platform for self-driving cars and autonomous vehicles by exploring and integrating best industry practices
Coding mostly in Python, basic understanding of HTML and Vue.js is welcomed, but not required
Creating tools for synthetic datasets generation
Proactively solving technical challenges and fixing bugs
Collaborating with our Enterprise customers and Community Users to help them customize Supervisely platform by building Supervisely Apps
Contributing ideas and constructive feedback to our product development roadmap
Improving documentation, creating guides and tutorials for our developer portal
We are looking for:
2+ year in Python software development
Experience in autonomous vehicles industry or willingness to become an expert in 3D
Knowledge of major Python libraries like Numpy, Pandas, requests, sklearn, OpenCV
Good understanding of modern developer tools: docker, git, github, vscode, venv
Strong principles towards writing clean, simple and maintainable code
Good verbal and written communication skills in English
Good background in mathematics and linear algebra
You will get extra credits for:
Experience in 3D Data Processing libraries like Open3D or others
Experience in neural networks and other algorithms for 3D, e.g. tracking, interpolation, etc...
Understanding of popular formats and how sensor fusion (LiDAR + cameras) works
Development of your own Python library / repository or participating and contributing in a popular one
Familiarity with any cloud systems (AWS, Azure, Google app engine)
Familiarity with visualization on maps widget (e.g. openstreetmap)
University degree in a technical subject (Computer science, Mathematics, or similar) or equivalent experience in the industry
Experience creating tutorials, videos or technical blog posts
Experience in building your own startup or product
Why you’ll love it here:
Play a direct role in shaping the future of building Computer Vision solutions
Working on Supervisely App Engine - the new way of building python single page web applications that can be also used outside Supervisely
Accelerate your professional growth by solving challenging development tasks
Contribution to open-course: Supervisely Python SDK and all Apps in our Ecosystem are open-sourced
Impact and work with our growing community of 65k+ companies, researchers and developers worldwide
Work closely and solve real tasks with our customers — leading companies in various industries like autonomous vehicles, agriculture, medicine and manufacturing
Intensive knowledge sharing with our extremely talented web-development team
Apply for the role now! We kindly ask you to complete this Google Form to continue. Please make sure to answer all the questions provided to help us better understand you — and we will get back in time!