Senior Software Engineer, AI Infrastructure

Description

The company builds Kubernetes-native AI infrastructure that lets organizations run scalable, secure, sovereign platforms on-premises, in the cloud, at the edge, or in sovereign data centers, with an emphasis on open standards and no lock-in.

The company is part of IREN. This role sits on the AI infrastructure team and focuses on running LLM inference on Kubernetes for enterprise customers.

Responsibilities

• Build LLM serving systems on Kubernetes, covering deployment, GPU scheduling, autoscaling, and managing model lifecycles.
• Make the platform installable and upgradable in enterprise environments, including restricted and offline networks, using Helm.
• Connect the serving layer to the platform's API gateway, identity, and metering services.
• Create monitoring for running GPU inference in production, including serving metrics and GPU telemetry.
• Work across a multi-service codebase and help shape engineering direction through design documents and code reviews.

Requirements

• 5+ years of software engineering experience in infrastructure, platform, or distributed systems.
• Hands-on experience running production workloads and writing Helm charts on Kubernetes, not only using managed clusters.
• Experience with GPU workloads or LLM inference, or strong adjacent systems experience and a record of picking up new areas quickly.
• Strong Go skills, plus solid experience with CI/CD and infrastructure as code.
• Daily use of AI-assisted development tools such as Claude Code or OpenAI Codex.
• Able to work with a high degree of autonomy on a small, remote-first team that relies on written communication.
• Inference performance work such as quantization, batching, or caching, or experience with distributed serving frameworks.
• Enterprise deployment experience, such as air-gapped installs, SSO/OIDC, or supply-chain security.
• UI development experience, for example with React or TypeScript; useful as the product's management interfaces grow.
• Open-source contributions in the Kubernetes or ML infrastructure ecosystems.

Conditions

Remote-first role on a small team with a written culture.

The company is young and moves quickly, and it values openness, collaboration, calculated risk, and continuous learning.

Benefits

• Work alongside an experienced cloud infrastructure company in Silicon Valley and a passionate, skilled team serving Fortune 500 and Global 2000 customers.
• Contribute to cutting-edge open-source projects.
• Professional development and training.
• Opportunities to attend conferences and working groups.
• Company outings, happy hours, hackathons, and tech talks.
• A competitive compensation package with a strong benefits plan.