As a senior computer vision engineer on our team, you will be working with cutting-edge technology to deploy real-time computer vision solutions at scale. We are pushing the bounds of existing deep learning technology to deploy real-time CV solutions on embedded devices. You will be working on a variety of machine learning and computer vision problems and deploying models to real-world customers.

We use Tensorflow as our deep learning framework, run distributed training loads in GCP and AWS, and prototype post processing functions in Cython before moving them to C++ for the Edge Computing team. We also do a lot of classical computer vision / robotics, mostly in Python and C++.

‍

Recent projects for this role include:

• Writing a machine learning pipeline from scratch based on a paper released on Arxiv. Includes the dataset loader, augmentation functions, deep learning model, and loss functions -- the whole nine yards. And that was just a Tuesday.
  
• Helping a junior CV engineer debug a pipeline similar to above
  
• Working on novel labeling methods with data infrastructure to reduce labeling costs while improving model outputs
• Implementing new loss functions or model architectures so cool they would make waves at CVPR, when you deign to eventually share them
• Writing an algorithm to calibrate three depth cameras into the same frame, using information from a deep learning algorithm as points in common, to allow for magical automatic calibration in the wild

‍

An ideal candidate would:

• Have built or worked on deep learning training pipelines
• Have worked on frame transformations, camera calibration, optical flow, etc.
• Have the ability to quickly hit the ground running and build training pipelines
• Be passionate about AI and is ready to take risks in a fast-paced startup environment

As a  full-stack engineer on our team, you will have the opportunity to build and deploy the infrastructure necessary for real-time computer vision solutions. You will be exposed to state-of-the-art AI and machine learning pipelines and contribute to the success and scalability of these systems. You will work on multiple pipelines from internal machine learning tools to customer-facing dashboards.

We use Python for our backend server and pipeline automation scripts, Typescript and React for our web apps, and AWS for all our cloud needs (DynamoDB, Kinesis Data Streams, CloudFront, etc.)

‍

Recent projects for this role include:

• Building a data management pipeline to manage and label terabytes of data for our machine learning team
• Designing a new human pose labeling tool to reduce cost by 50x (and it's now being patented)
• Developing a dashboard to visualize real-time data from our camera infrastructure
• Architecting and developing an isolated health infrastructure to monitor our massively distributed platform

‍

An ideal candidate would:

• Have built or worked on production web applications, including work on the frontend, databases and backend frameworks
• Have the ability to quickly hit the ground running and scaling our infrastructure in a modular fashion
• Be passionate about AI and is ready to take risks in a fast-paced startup environment