Software Engineer - Observability

About this role

Build and evolve observability systems that help teams monitor, diagnose, and resolve issues across Baseten’s growing multi-cloud infrastructure. The role focuses on scalable telemetry pipelines, reliable storage, and tools that improve operational visibility and incident response.

About the company

Baseten is an inference cloud that helps companies run and scale AI models in production with flexible infrastructure and developer tooling.

The team

Observability team within the Infrastructure organization.

Stack

What you'll do

• Build scalable ingest and storage pipelines for metrics, logs, and traces.
• Improve observability platform reliability, cost efficiency, and scalability.
• Develop instrumentation libraries, SDKs, and integrations.
• Build alerting and SLO infrastructure.
• Partner with teams across Inference, Product, and Infrastructure.

What we're looking for

• Deep experience in at least one observability signal area and familiarity with others.
• Understanding of high-throughput data pipelines, columnar storage, and telemetry tradeoffs.
• Experience with observability platforms such as Prometheus, Grafana, ClickHouse, or OpenTelemetry.
• Strong proficiency in Python, Rust, or Go.
• Strong communication and cross-team collaboration skills.
• Comfort working independently on ambiguous infrastructure challenges.

Nice to have

• Interest in applying AI or LLMs to root-cause analysis, anomaly detection, or intelligent alerting.

Benefits

• Equity
• Medical, dental, and vision coverage for employees and dependents in the U.S.
• Flexible PTO and company-wide winter break
• Paid parental leave
• Fertility and family-building stipend
• Company-facilitated 401(k) in the U.S.