Platform Engineer, AI Inference
modularai
Modular is seeking a Platform Engineer to enhance their AI infrastructure, focusing on multi-cloud services and AI deployment. The role involves hands-on development and technical leadership within the Platform Engineering group, which supports collaboration across the company. Candidates can work remotely or from the Los Altos, CA office, with a focus on building scalable AI inference systems.
Qualification
- 5+ years of relevant experience
- Experience maintaining Kubernetes clusters and applications
- Experience building, deploying, and supporting cloud services (bonus points for multi-cloud)
- Comfort working across clouds, tools, and systems—focusing on problem-solving rather than specific technologies
- Strong collaboration skills and ability to share knowledge
Responsibility
- Shape the technical platform for large scale AI inference
- Promote technical and team excellence through collaboration and leadership
- Develop and maintain core platform capabilities — traditional and high performance networking, k8s clusters, etc
- Support development teams with infrastructure needs
- Implement security best practices across systems
