Observability Engineer for Scalable AI Infra

Baseten; Montreal (administrative region); On-site; CAD 230,000 - 460,000; Full time

Benefits offered by this job

Competitive compensation

Equity

Health insurance

Flexible PTO

Parental leave

Fertility stipend

401(k)

ML startup exposure

Job summary

Baseten is seeking talented Software Engineers to join the Observability team within the Infrastructure organization. You will build high‑throughput telemetry ingest pipelines, cost‑efficient storage, and diagnostic tools to detect and resolve issues quickly as Baseten scales.

You’ll own core observability platforms, instrument libraries, and alerting/SLO infrastructure while partnering with product, inference, and infrastructure teams to meet diverse organizational needs.

Qualifications

• Experience with at least one observability signal area (metrics/logging/tracing/error analytics).
• Knowledge of high-throughput data pipelines and columnar storage for telemetry data.
• Experience with observability platforms (Prometheus, Grafana, ClickHouse, OpenTelemetry).
• Proficiency in Python, Rust, or Go.
• Strong communication and collaboration with internal teams.
• Interest in applying AI/LLMs to operational workflows.
• Comfort with building foundational infrastructure and solving ambiguous problems.

Responsibilities

• Design and build scalable telemetry ingest and storage pipelines across multi-cloud infrastructure.
• Own observability platforms; drive migrations and architectural improvements for reliability and cost efficiency.
• Build instrumentation libraries and integrations for emitting telemetry from services.
• Develop alerting and SLO infrastructure to monitor reliability with minimal noise.
• Collaborate with Inference, Product, and Infrastructure teams to meet diverse needs.

Skills

Metrics

Logging

Tracing

Python

Rust

Go

Prometheus

Grafana

OpenTelemetry

Tools

ClickHouse

Prometheus

Grafana

OpenTelemetry

Telemetry SDKs

Job description

Baseten is seeking talented Software Engineers to join the Observability team within the Infrastructure organization. You will build high‑throughput telemetry ingest pipelines, cost‑efficient storage, and diagnostic tools to detect and resolve issues quickly as Baseten scales.

You’ll own core observability platforms, instrument libraries, and alerting/SLO infrastructure while partnering with product, inference, and infrastructure teams to meet diverse organizational needs.