Site Reliability Engineer (SRE)

Baseten is a company that powers mission-critical inference for dynamic AI companies. As a Site Reliability Engineer, you will build robust systems and processes to ensure scalable, reliable, and efficient infrastructure, while collaborating closely with users to improve the platform.

Responsibilities:

• Build and maintain scalable infrastructure to support the deployment and operation of machine learning models
• Establish standards and best practices for reliability and performance across the infrastructure
• Automate processes when relevant, particularly for managing CI/CD pipelines
• Own products and projects end-to-end, functioning as both an engineer and a project manager, with a focus on user empathy, project specification, and end-to-end execution
• Collaborate with cross-functional teams to understand project requirements and translate them into technical solutions
• Mentor junior team members and contribute to knowledge sharing within the organization
• Navigate ambiguity and exercise good judgment on tradeoffs and tools needed to solve problems, avoiding unnecessary complexity
• Demonstrate pride, ownership, and accountability for your work, expecting the same from your teammates

Requirements:

• Bachelor's, Master's, or Ph.D. degree in Computer Science, Engineering, Mathematics, or related field
• Extensive experience with Kubernetes
• Experience in building and maintaining scalable infrastructure
• Experience with infrastructure-as-code tools (e.g., Terraform, CloudFormation, Pulumi) and CI/CD tooling (e.g., GitHub Actions, GitLab CI, Circle CI, Jenkins)
• Ability to own projects end-to-end, from project specification to execution
• No prior machine learning experience required, but should be open to learning about it
• Relevant OSS observability experience (Prometheus, ELK stack, Grafana stack, Opentelemetry) is a plus