Primary job responsibilities will include the following
Architect and lead implementation of scalable solutions with distributed computing capabilities to deploy, train, and serve ML models on OpenShift AI (RHOAI)
Drive end-to-end execution of small-scale, cross-team and partner initiative
Build multi product demos and AI/ML workflows using Predictive and Generative AI leveraging RH product and AI stack
Build, deploy , optimize and otherwise improve Agentic AI workflows running on OpenShift AI
Work with upstream AI/ML communities to evaluate new AI/ML-related technologies from partners and create examples of integrations between their technology and RHOAI
Collaborate with AI/ML partners to adjust their AI strategies, address their specific use cases, and drive value through the adoption of the RHOAI
Required Skills
Experience in development in Python or Go
Experience of containers and OpenShift or Kubernetes
Experience and knowing AI frameworks and libraries (e.g. OpenDataHub, TensorFlow, PyTorch, Kueue, KubeRay, KubeFlow, CodeFlare, Feast etc)
Familiarity with model parallelization, quantization, and memory optimization using vLLM, DeepSpeed, OpenVino and other inference libraries
Experience with AI and MLOps tools and Concepts, including Automation, GitOps, pipelines, models, etc. for managing the AI/ML lifecycle in production environments
Interest in learning new technologies; problem-solving skills.
The following are considered a plus
Cloud Computing experience using at least one of the following Cloud infrastructures AWS, GCP, Azure & IBM Cloud
Previous code contributions to or participation in open source projects or code samples on GitHub.
משרות נוספות שיכולות לעניין אותך