ABOUT BASETEN

We're a growing team of builders backed by top-tier investors including IVP, Spark Capital, and Sarah Guo at Conviction. ML teams at enterprises and category-defining AI-native companies like Descript, Bland, and Patreon use Baseten to power their core production workloads with best in class performance, security, and reliability. While we've unlocked PMF and secured Series B funding, the ML infrastructure market is massive and we're just getting started. If you're excited to work on engaging and relevant problems while building something new from the ground up, come join us!

As a Site Reliability Engineer, you'll envision and build robust systems and processes that ensure our infrastructure is scalable, reliable, and efficient. This can range from automating deployments and monitoring systems to optimizing performance and managing incidents.

We all work closely with our users, learning from their past struggles in operationalizing ML, onboarding them onto our platform, and turning our learnings into ideas for improving Baseten.

AS A SITE RELIABILITY ENGINEER, YOU:

• Have experience building and maintaining scalable infrastructure.

• You have extensive experience with Kubernetes.

• Know when automation is your friend, and apply it when relevant, e.g. for managing CI/CD pipelines

• Have experience establishing standards and best practices for reliability and performance.

• Don't need to have prior ML experience, but are open to learning about it.

• Bonus Points: Relevant OSS observability experience (eg prometheus, ELK stack, grafana stack, opentelemetry)

YOU ALSO:

• Can own products and projects end-to-end; engineers and designers at Baseten also function as PMs, so we'd like everyone on the team to be able to empathize with our users, understand/write project specs, and manage the end-to-end execution of projects.

• Are comfortable with navigating ambiguity and enjoy the journey as much as the destination.

• Are motivated by customer problems and find joy in creating simple, elegant solutions that avoid unnecessary complexity.

• Exercise good judgment on tradeoffs and tools needed to solve the problem and don't over index on trendy/fashionable tech unless it's the right tool for the job.

• Demonstrate pride, ownership, and accountability for your work and expect the same from your teammates.

OUR CURRENT TECH STACK:

Backend — Go, Python, Postgres

Platform — Kubernetes, Go, Postgres, Redis, Kafka

Infrastructure — Gitops, Flux, Terraform, AWS/GCP