Exploring, Inventing and Optimizing of AI workflows

During the next few years AI will be heavily deployed in the Cloud, the Edge and the Fog. NeuReality is an innovative system and semiconductor startup focusing on the future challenges of this growing demand by designing the next evolution of AI-as-a-Service Infrastructure.

To achieve best AI inference performance, AI developers convert Deep Learning models to target HW (CPU, GPU, ASIC). At Neureality we are developing AI modules and defining developers AI workflows to make this conversion process easy, intuitive and effective and manage complete AI pipelines (multiple AI models running is sequence).

We are looking for a broad minded, capable, experienced AI tech leader to lead this project.

Responsibilities:
* Define AI developer user experience for converting AI models and pipelines to target HW.
* Design and build tools to implement the developer user experience.
* Select AI use cases and workloads, load them on CPU and GPU system, measure performance (CPU, memory, etc.), optimize workloads.
* Work closely with Neureality software team to integrate AI tools with middleware and hardware.


The person we are looking for should have:
• Extensive proven experience working with AI frameworks (TensorFlow, PyTorch etc.)
• Extensive proven experience building and deploying AI models on various platforms and architectures (cloud, edge, GPU, TPU)
• Hands-on Python coding. C/C++ experience is a big advantage.
• Experience working with AI models formats (SavedModel, ONNX, Pytorch).
• Experience with AI cloud services (AWS SageMaker, Google CloudML, etc.)
• Problem solver with good communication skills.

Project scope & work environment:
• Initial project scope is 2 months which can be extended based on progress.
• The project is innovative by nature. This means that project definitions may change overtime and that you will work closely with Neureality software team.