1 day ago
Remote, United States or Austin, TX, USAStaff+
Responsibilities
- Own the architecture of the AI gateway, control plane, model serving, identity, metering, and observability across hosted and installed editions.
- Lead gateway strategy, including data-plane selection, policy-based routing, per-request metering, and audit records.
- Set the technical direction for LLM serving on Kubernetes, including GPU scheduling and sharing, autoscaling, multi-tenancy, disaggregated serving, and cost per token.
- Define enterprise deployment capabilities such as Helm installations and upgrades, air-gapped networking, preflight checks, and supply-chain security.
- Build hands-on in critical-path areas, run design reviews, make build-versus-buy decisions, and record architectural decisions as ADRs.
- Set the technical bar for a small senior remote-first team and mentor senior engineers, including on AI-assisted development.
- Collaborate with design partners and customers and represent Mirantis in Kubernetes and ML-infrastructure communities.
Requirements
- 10+ years of experience in infrastructure or distributed systems, including several years as a technical lead.
- Experience shipping multi-service systems used by enterprises in production, including software customers install themselves.
- Expertise with Kubernetes operators, CRDs, scheduling, Helm, and debugging at scale.
- Production experience with GPU workloads, LLM inference, or AI gateways.
- Expert Go skills, strong Python skills, and experience with CI/CD and infrastructure as code.
- Experience leading through writing and influence and working autonomously on a distributed team.
- Fluency with AI-assisted development tools.
- Preferred experience with inference performance topics including quantization, batching, KV-cache management, and disaggregated prefill and decode.
- Preferred experience with AI gateway or LLM routing capabilities such as failover, rate limiting, token metering, and policy enforcement.
- Preferred experience taking a new product to its first enterprise customers.
Benefits
- Competitive compensation package with a strong benefits plan.
- Remote-first work environment.
- Opportunity to work with an established cloud infrastructure leader and Fortune 500 and Global 2000 customers.
- Work on open-source, Kubernetes-native AI infrastructure and next-generation cloud technologies.
- Collaborative, high-energy environment emphasizing openness, risk-taking, and continuous growth.
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.