SRE (AI Inference Infrastructure)

Location: San Francisco Bay Area or Toronto, United States/Canada

Company

hirify.global builds high-performance AI hardware and infrastructure for training and inference workloads.

What you will do

• Execute production releases, capacity changes, and cluster upgrades while the SRE function scales.
• Develop self-service continuous delivery pipelines using Kubernetes, Bazel, Prometheus, Grafana, InfluxDB, Python, and Go.
• Build reusable automation and internal developer tools to reduce operational toil and cross-team friction.
• Develop telemetry, observability, and alerting solutions for reliable operations at scale.
• Collaborate with Cluster Ops and development teams to identify and implement high-impact automation.
• Contribute to SLOs, post-mortems, reliability metrics, and capacity planning.

Requirements

• 2–4+ years of SRE experience with a strong operations or automation focus.
• Production experience with Kubernetes.
• Proficiency in Python or Go for tools and automation.
• Experience with Prometheus, Grafana, and observability-driven workflows.
• Ability to measure and communicate reliability, operational toil, and velocity impact.

Nice to have

• Hands-on GitOps experience with Argo CD, Flux, or an equivalent tool.
• Experience building continuous delivery pipelines.
• Experience with Bazel or similar build systems.
• Familiarity with capacity planning and on-premises or multi-datacenter environments.

Culture & Benefits

• Work on a high-performance AI platform and wafer-scale computing architecture.
• Opportunity to work with cutting-edge AI infrastructure and leading model builders.
• Direct mentorship from experienced engineers and ownership of production systems.
• No requirement for 24/7 on-call rotations.
• Startup vitality, job stability, and a simple, non-corporate work culture.
• Continuous learning, growth, and support in an inclusive workplace.