Data Scientist, DICOM

Work in Supervisely Data Scientist, 3D Point Cloud We are building a top data science team focused on computer vision and are looking for exceptional people to work with us. You will enjoy an opportunity to train and apply state-of-the-art models to various real world tasks, design custom training and inference pipelines, integrate neural networks into Supervisely and share them with the entire ML community. In addition, we are doing cutting-edge research in various directions, including labeling automation, AI-assisted tools to speed up data annotation, synthetic datasets, human-in-the-loop, active learning, GANs, and many more. Most common modality to work will be 2D and 3D medical images. Machine Learning Remote Apply for role Other roles About Supervisely 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
Watch video about Supervisely’s main principles from our CEO Yuri Borisov: Learn More Here Try Community Edition
Explore apps in Supervisely Ecosystem
Find technical details in our Developer portal
Your Daily Adventures Will Include Creating Supervisely Apps, main areas include development of Data Pipelines for medical volumes and Machine Learning models infrastructure
Working with top github repositories with state-of-the-art models, train, test, deploy and integrate them into Supervisely
Coding mostly in Python, basic understanding of HTML and Vue.js is welcomed, but not required
Handling the entire model lifecycle: data preparation, training, inference, model debugging, comparison, deployment. Building special ML tools for work automation and publish them in our Ecosystem
Experiment with modern research, explore SOTA papers and conferences
Proactively solving technical challenges and fixing bugs
Contributing ideas and constructive feedback to our product development roadmap
Sharing your knowledge with community developers by creating tech videos, blog posts and promoting appropriate tech and engineering best practices in and outside of the team
Collaborating with Enterprise customers to help with integration and building customized data and model pipelines
Improving documentation, creating guides and tutorials for our developer portal
We Are Looking For Industry experience in data science and machine learning (1+ years recommended)
Knowledge of major Python libraries like Pytorch, Tensorflow, Numpy, Pandas, requests, sklearn, OpenCV
Solid understanding of modern developer tools: docker, git, github, vscode, venv
Good principles towards writing clean, simple and maintainable code
Good verbal and written communication skills in English
Leveraging our in-house data and model platform that allow you to perform experiments in a matter of days
You Will Get Extra Credits For Participating and winning Kaggle competitions
Experience in NN frameworks designed for volumes and understanding medical data formats (dicom, nrrd, nifti, etc)
Experience in organizing dataset creation from scratch, experimentation with GANs or synthetic data
Experience in building client-server apps using FastApi, Flask, Uvicorn or others
Development of your own Python library / repository or partici