ML Ops Engineer
$100k - $225k • 0.50% - 2.50%
Overview is a company that takes the cutting edge in computer vision and deep learning and applies it to previously unsolvable manufacturing inspection problems. We are truly a full stack company. We install physical cameras into the facility, run inference on the edge and manage massive deployments. Overview also streams gigabytes of video/image data to the cloud for our web platform to give customers advanced insights and analytics.
We are looking for engineers who like to solve tough challenges across the stack. This might include wrangling 500mb images or deploying optimized models in one click that can handle 10 parts a second. We are looking for people who are dynamic, who are excited to work on a different challenge every week, whether it's the final inspection on a medical device or making sure a razor blade has a perfect edge.
Skills: Python, SQL, TensorFlow, Deep Learning, Computer Vision, Amazon Web Services (AWS), OpenCV
At Overview we are building an end-to-end computer vision platform to democratize manufacturing's access to state of the art deep learning. Delivering on reliable and accurate models is a key component of this. We are looking for someone who knows the ins and outs of DL infra. Hands on responsibilities will include:
- Implement a high-efficiency CV/DL pipeline, including identifying and solving for bottlenecks
- Choosing and implementing the best tools to strengthen our pipeline
- Collaborate with our DL engineers to get high performing models into customers hands
- Build, manage, scale our training pipeline
- Developing tools that monitor models to ensure long term stability and accuracy
- Figure out how to built models that don't drift, can adapt to changes, etc...
- Having deployed models to several platforms including edge devices and cloud
- Having managed an end to end deep learning project from data collection to deployment
- Experience with Docker
- Experience with Python/C++
Overview's tech is far reaching. We deploy highly reliable camera hardware and GPU's into manufacturing and industrial settings. We have an IoT fleet management stack to update, secure, and manage our fleet of devices. We stream this data to our cloud or to a customers hybrid cloud where we have a user facing platform where customers can interact with their devices, deploy new deep learning models, and see advanced analytics.
We use Docker to deploy web infrastructure and deep learning models. We have an extensive deep learning stack using Tensorflow, PyTorch and packaged with Onnx. Our frontend is in React, which is updated in real time from our fleet using MQTT. And the list goes on...