Red hat Senior ML Engineer - OpenShift AI Observability 

Israel, Center District, Raanana 

202797401

What you will do

• Design and build observability and optimization tools for large-scale GenAI workloads running on Kubernetes

• Develop systems to collect and analyze model performance metrics, logs, and resource usage in real-time

• Innovate in the MLOps and AI observability domain by contributing to upstream communities

• Collaborate with product, engineering, and research teams to improve model trust and performance

• Write unit and integration tests and work with quality engineers to ensure product quality

• Use CI/CD best practices to deliver solutions into RHOAI as part of our productization efforts

• Contribute to a culture of continuous improvement by sharing technical knowledge and insights

• Communicate effectively with stakeholders and team members to ensure visibility of ML performance

• Represent RHOAI in external engagements including open source communities and customer meetings

• Mentor and guide junior engineers and contribute to team growth

What you will bring

• Experience in machine learning engineering, with a focus on production-grade systems

• Proficiency in Python with a focus on AI/ML infrastructure or tooling

• Experience working with Kubernetes, OpenShift, or other cloud-native platforms

• Familiarity with ML observability tools (e.g. Prometheus, OpenTelemetry, and Grafana)

• Hands-on experience with source control tools such as Git

• Passion for open-source technology and collaborative development

• Strong troubleshooting skills and system-level thinking

• Ability to work autonomously and thrive in a fast-paced environment

• Excellent written and verbal communication skills

The following will be considered a plus:

• Master’s degree or higher in computer science, machine learning, or related discipline

• Contributions to open-source projects, especially in the MLOps or ML observability domain

• Experience with public cloud services (AWS, GCP, Azure)

• Background in developing or deploying MLOps platforms or AI monitoring tools