Senior AI Inference & Runtime Platform Engineer (Remote)

Uncover; Seattle, Northern (WA, KY); Hybrid; USD 150,000 - 210,000; Full time

Benefits offered by this job

Health insurance

Bonus eligibility

Equity

Fully remote culture

Job summary

AZX is building an AI transformation platform with secure, hardware-isolated execution for agent-generated code. You will own the layer where AI workloads run, including inference control plane, sandboxed microVMs, and multi-substrate model lifecycles, using Rust, Kubernetes, and fast control-plane services.

You will work across managed GPU clouds and customer Kubernetes clusters, ensuring security, efficiency, and scale for open-weight models while building tools and dashboards for the backend

Qualifications

• 5+ years shipping production systems in a systems language.
• Strong threat-modeling of isolation boundaries and least privilege.
• Experience operating Kubernetes workloads with controllers or operators.

Responsibilities

• Manage the serving tier for open-weight models: deployment, config, and SLOs.
• Administer Kubernetes layer for inference and sandbox workloads, autoscaling and GPU scheduling.
• Own the stateful data plane: vector stores and graph stores with backup and restore.
• Oversee sandbox runtime and host-side control plane: lifecycle, exec, teardown, metering, approvals on writes.
• Direct the FastAPI control-plane services and infra-as-code assets (Terraform/OpenTofu, Bicep).
• Maintain OSS posture: release processes, docs, reproducible builds.

Skills

Rust

Go

C/C++

Kubernetes

Security design

Tools

vLLM/SGLang

KEDA

Kubebuilder/CRDs

Terraform/OpenTofu

OpenTelemetry

Job description

AZX is building an AI transformation platform with secure, hardware-isolated execution for agent-generated code. You will own the layer where AI workloads run, including inference control plane, sandboxed microVMs, and multi-substrate model lifecycles, using Rust, Kubernetes, and fast control-plane services.

You will work across managed GPU clouds and customer Kubernetes clusters, ensuring security, efficiency, and scale for open-weight models while building tools and dashboards for the backend