Platform Engineer

About the Role

As a Platform Engineer at Aurelian, you’ll help design and scale the infrastructure behind our life-saving voice AI systems. This includes building multi-region, highly available systems, supporting real-time voice workloads, and managing infrastructure for AI models — including containerized GPU workloads.

You’ll play a critical role in ensuring our systems are reliable, fast, and scalable as we continue to expand nationwide.

What You’ll Do

• Scale infrastructure to support millions of voice interactions across U.S. call centers.

• Enhance our multi-region architecture to reduce latency and improve uptime.

• Design and maintain infrastructure for self-hosted, GPU-based AI workloads.

• Improve our monitoring, alerting, and observability to support mission-critical systems.

• Collaborate across teams to build deployment pipelines and support product delivery.

• Automate infrastructure using Terraform (or similar IaC tools) and manage Kubernetes clusters.

What You Need

• 3+ years of experience in DevOps, SRE, or Platform Engineering roles.

• Proven experience running and managing Kubernetes clusters in production.

• Experience deploying and operating containerized GPU workloads.

• Experience with cloud providers (AWS, GCP, or Azure).

• Familiarity with observability tools (e.g., Prometheus, Grafana, Datadog).

• Solid scripting or programming skills — Python preferred.

• Versatility and willingness to step outside your domain when needed (e.g., backend contributions).

Bonus Points

• Experience with real-time communication systems (e.g., WebRTC, SIP, or voice AI platforms).

• Knowledge of telecom, emergency services, or regulated environments.

• Familiarity with multi-tenant and multi-region architectures.

Benefits

• Competitive salary and meaningful equity

• Medical, dental & vision insurance coverage

• Unlimited PTO

• WFH stipend for your home office

• Relocation stipend

Ready to Help Fix 9-1-1?

If you’re excited about improving critical infrastructure, scaling real-time AI systems, and doing work that genuinely helps people — we’d love to talk.