Observability Engineer: Scalable Telemetry & AI Alerts

Baseten; United States; Remote; USD 140,000 - 210,000; Full time

Job summary

Baseten is seeking software engineers to join our Observability team within the Infrastructure group. You will help build the observability experience for internal and external customers, improving reliability and operational excellence across Baseten's platforms.

As we scale across cloud providers and hardware, you will develop high-throughput ingest pipelines, efficient storage, and diagnostic tools to detect, diagnose, and resolve issues quickly.

Qualifications

• Deep experience in at least one observability signal area (metrics, logging, tracing, or error analytics).
• Familiarity with other signals and scale data pipelines.
• Experience with Prometheus, Grafana, OpenTelemetry or similar systems.

Responsibilities

• Design and build scalable telemetry ingest and storage pipelines for metrics, logs, and traces across Baseten's multi-cloud infrastructure.
• Own and evolve core observability platforms, driving migrations and architectural improvements to improve reliability and reduce cost.
• Build instrumentation libraries, SDKs, and integrations that help engineers emit high-quality telemetry from services.
• Drive alerting and SLO infrastructure enabling teams to monitor and respond to reliability targets with minimal noise.
• Partner with Inference, Product, and Infrastructure teams to tailor observability solutions to needs across the org.

Skills

Python

Rust

Go

Tools

Prometheus

Grafana

ClickHouse

OpenTelemetry

Job description

Baseten is seeking software engineers to join our Observability team within the Infrastructure group. You will help build the observability experience for internal and external customers, improving reliability and operational excellence across Baseten's platforms.

As we scale across cloud providers and hardware, you will develop high-throughput ingest pipelines, efficient storage, and diagnostic tools to detect, diagnose, and resolve issues quickly.