This role is _less about coding_ and _more about architecture, pipelines, orchestration and high load_.
Nice to have (or able to learn quickly):
* Linux, Docker, AWS or GCP, gcc/make
* Apache Airflow
* Linux system administration and performance analysis
We work with challenging commercial / industry projects involving complex Machine Learning pipelines, mainly focusing around Computer Vision. Your job will be to help design, set up, run and maintain such ML pipelines at our server infrastructure.
Senior candidates expected to have experience with ML toolkits:
* ONNX Runtime
Please also mention if you have worked with:
* Triton Inference Server (TensorRT Server)
* Kubeflow / kfserving
We are a startup focused on Computer Vision and Machine Learning