Senior SRE: AI Compute, Kubernetes & Observability

Justjoin; United States; Remote; USD 140,000 - 190,000; Full time

Benefits offered by this job

Health benefits

Financial planning

Family benefits

Work-life balance

Time for other pursuits

Job summary

Justjoin seeks a Senior SRE to own reliability workstreams for a serverless inference platform, build automation, and drive architecture and operational decisions. You will partner with product engineering to scale GPU infrastructure and AI workloads using Kubernetes at scale.

You will lead observability efforts, implement automation to reduce toil, and contribute to incident management with runbooks and blameless post-mortems.

Qualifications

• Expertise in SRE, infra, or platform engineering for large-scale distributed systems.
• Kubernetes and large-scale containerization experience.
• Define SLOs and use observability tools (Prometheus, Grafana, tracing).
• Proficiency in Python or Go for automation and IaC (Terraform).
• Interest in AI/ML infra, model serving, or GPU workloads.
• Independent problem solver with accountability.
• Collaborate with teams unfamiliar with SRE practices.

Responsibilities

• Building and maintaining observability for AI workloads, including telemetry, dashboards, alerts, SLO/SLI tracking, and driving improvements when targets are missed
• Writing automation and tooling to reduce operational toil, improve deployment safety, and accelerate incident response
• Integrating AI workloads into our existing incident management processes, building runbooks, participating in on-call rotations, and conducting blameless post-mortems
• Building and maintaining CI/CD integrations, deployment safety checks, and rollback automation
• Collaborating with product engineering teams to improve reliability, contribute to architecture decisions, and ensure operational readiness for product releases
• Contributing to capacity planning, autoscaling configuration, and workload scheduling for AI compute infrastructure

Skills

SRE practices

Automation

Observability

On-call experience

Tools

Kubernetes

Terraform

Prometheus

Grafana

Distributed tracing

Job description

Justjoin seeks a Senior SRE to own reliability workstreams for a serverless inference platform, build automation, and drive architecture and operational decisions. You will partner with product engineering to scale GPU infrastructure and AI workloads using Kubernetes at scale.

You will lead observability efforts, implement automation to reduce toil, and contribute to incident management with runbooks and blameless post-mortems.