Freelancers required to set up a non-standard Kubernetes AI inference cluster

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.

We are setting up system to demonstrate high throughput, low latency AI inference on the cloud. The system has the following characteristics/requirements:
• Multiple-clients/multiple-servers topology
• Using various network protocols
• Includes proprietary HW and drivers
• Runs over Kubernetes
• Controlled remotely to manage test setup and workflow.

We are looking for:
A Cloud, Docker and Kubernetes expert that will help us setup the systems in a correct, by the book, scalable manner and will help us overcome challenges arising from a non-standard Kubernetes setup.

The person we are looking for should have:
• Extensive proven experience setting up large scale complex Kubernetes clusters.
• Extensive proven experience setting up deployment pipelines including automated testing using Docker containers on the cloud.
• Good understanding of microservices architecture, git, Docker containers.
• Hands-on Python coding.
• Experience with setting up on-premises Kubernetes (not using a cloud provider)
• In depth understanding of Kubernetes architecture and networking.
• Problem solver with good communication skills.

Project scope & work environment:
• Project duration is 1 month with option for extension based on company needs.
• Phase one includes setting up a multi-client/multi-server configurable Kubernetes cluster.
• Proprietary HW and networking will be added as a second phase.
• Work will take place mostly at NeuReality offices in Caesarea and from home when possible.
• Project includes documentation and orderly knowledge transfer to NeuReality personnel.
• Project scope: Write client & server code, Setup cluster, Configure clients-servers topologies, Run simple task to verify connectivity per requested topology, Setup deployment pipeline