Red Hat is looking to develop robust infrastructure and tools for trustworthy large language models and agentic workflows, and to make machine learning model deployment and monitoring seamless, scalable, and trustworthy across the hybrid cloud and the edge.
Requirements
- 5+ years of software engineering experience, with at least 4 years focusing on ML/AI systems in production environments
- Strong expertise in Python, with demonstrated experience building and deploying production ML systems
- Deep understanding of Kubernetes and container orchestration, particularly in ML workload contexts
- Extensive experience with MLOps tools and frameworks (e.g., KServe, Kubeflow, MLflow, or similar)
- Track record of technical leadership in open source projects, including significant contributions and community engagement
- Proven experience architecting and implementing large-scale distributed systems
- Strong background in software engineering best practices, including CI/CD, testing, and monitoring
Responsibilities
- Lead the architecture and implementation of MLOps/LLMOps systems within OpenShift AI, establishing best practices for scalability, reliability, and maintainability while actively contributing to relevant open source communities
- Design and develop robust, production-grade features focused on AI trustworthiness, including model monitoring, bias detection, and explainability frameworks that integrate seamlessly with OpenShift AI
- Drive technical decision-making around system architecture, technology selection, and implementation strategies for key MLOps components, with a focus on open source technologies like KServe and TrustyAI
- Define and implement technical standards for model deployment, monitoring, and validation pipelines, while mentoring team members on MLOps best practices and engineering excellence
- Collaborate with product management to translate customer requirements into technical specifications, architect solutions that address scalability and performance challenges, and provide technical leadership in customer-facing discussions
- Lead code reviews, architectural reviews, and technical documentation efforts to ensure high code quality and maintainable systems across distributed engineering teams
- Identify and resolve complex technical challenges in production environments, particularly around model serving, scaling, and reliability in enterprise Kubernetes deployments
Other
- 5+ years of software engineering experience
- Advanced degree in Computer Science, Machine Learning, or related field
- Experience working with distributed engineering teams across multiple time zones
- Public speaking experience at technical conferences
- Familiarity with AI governance and responsible AI practices
