6 hours ago
Remote, United States or Raleigh, NC, USASenior
Responsibilities
- Design and build LLM serving infrastructure on Kubernetes, including deployment, GPU scheduling, scaling, and model lifecycle management.
- Package the platform for enterprise environments through Helm-based installs, upgrades, and restricted or offline network support.
- Integrate the serving layer with API gateway, identity, and metering services.
- Build observability for production GPU inference, including serving metrics and GPU telemetry.
- Contribute across a multi-service codebase and influence engineering direction through design documents and reviews.
Requirements
- 5+ years of software engineering experience in infrastructure, platform, or distributed systems.
- Deep hands-on Kubernetes experience building and operating production workloads and Helm charts.
- Experience with GPU workloads or LLM inference, or strong adjacent systems experience with demonstrated ability to learn quickly.
- Strong Go programming skills and solid CI/CD and infrastructure-as-code skills.
- Daily fluency with AI-assisted development tools such as Claude Code and OpenAI Codex.
- Ability to work autonomously on a small, remote-first, written-culture team.
- Preferred: inference performance experience with quantization, batching, caching, or distributed serving frameworks.
- Preferred: enterprise deployment experience including air-gapped installs, SSO/OIDC, and supply-chain security.
- Preferred: React and TypeScript experience, or open-source contributions to Kubernetes or ML-infrastructure ecosystems.
Benefits
- Competitive compensation package with a strong benefits plan.
- Remote-first work environment with a written culture.
- Opportunity to work on open-source innovation and next-generation cloud and AI infrastructure for enterprise customers.
Tech Stack
Categories
About Mirantis
Mirantis builds Kubernetes-native infrastructure software and services for enterprises to run cloud, container, and AI workloads across on-premises, public cloud, and edge environments. It sells subscriptions, support, and managed services around products like Mirantis Kubernetes Engine and the Lens Kubernetes platform; the company acquired Docker Enterprise in 2019. Founded in 1999 and headquartered in Campbell, California, Mirantis is privately held and an IREN company serving global enterprises.