Senior AI Infrastructure Engineer - Kubernetes & LLMs (Remote)

SmartRecruiters, Inc.; United States; Remote; USD 180,000 - 240,000; Full time

Benefits offered by this job

Remote-first team

Open-source culture

Professional development

Conferences and talks

Competitive compensation

Job summary

Mirantis, an IREN company, is building enterprise AI infrastructure for running large language models on Kubernetes clusters. A small, senior team will own the model-serving layer and its path to production, with strong autonomy in a remote-first, written-culture environment.

You will design LLM serving infra, package for enterprise deployments, and integrate with API gateway, identity, and metering services while enabling observability and scalable GPU workloads.

Qualifications

• 5+ years of software engineering experience in infrastructure, platform, or distributed systems.
• Deep hands-on Kubernetes experience with production workloads and Helm charts.
• Experience with GPU workloads, LLM inference, or related systems and fast-learning ability.
• Strong Go programming skills and CI/CD / IaC expertise.
• Familiarity with AI-assisted development tools (Claude Code, OpenAI Codex).
• Ability to work autonomously in a remote-first, written-culture team.

Responsibilities

• Design and build LLM serving infrastructure on Kubernetes: deployment, GPU scheduling, scaling.
• Package platform for enterprise environments: Helm-based installs, upgrades, and restricted/offline networks.
• Integrate the serving layer with the platform’s API gateway, identity, and metering services.
• Build observability for operating GPU inference in production (serving metrics, GPU telemetry).
• Contribute across a multi-service codebase and help set engineering direction through design docs and reviews.

Skills

Kubernetes

Go

CI/CD

IaC

LLM / AI inference

GPU workloads

Distributed systems

Remote collaboration

Tools

Helm

Docker

Linux

Job description

Mirantis, an IREN company, is building enterprise AI infrastructure for running large language models on Kubernetes clusters. A small, senior team will own the model-serving layer and its path to production, with strong autonomy in a remote-first, written-culture environment.

You will design LLM serving infra, package for enterprise deployments, and integrate with API gateway, identity, and metering services while enabling observability and scalable GPU workloads.