Infrastructure Engineer - AI, Kubernetes & Edge Systems

UMATR; Austin (TX); On-site; USD 120,000 - 190,000; Full time

Job summary

UMATR is hiring an Infrastructure Engineer to own platform deployment and scaling across Kubernetes, GPU infrastructure and cloud environments. As an early engineer, you’ll shape architecture and tooling with high ownership from day one.

You’ll manage end-to-end deployment, build Kubernetes on-prem deployments, implement GitOps, and own CI/CD pipelines and AI inference workloads on customer hardware.

Qualifications

• Strong Kubernetes expertise with troubleshooting production environments.
• Hands-on with Kubernetes on-prem deployments (k3s, RKE2, MicroK8s or similar).
• Production experience with Terraform and Docker in CI/CD.
• Experience running AI/ML workloads on GPU infrastructure.
• Own CI/CD pipelines and software delivery improvements.
• Strong Linux/Bash skills and Python for applications.

Responsibilities

• Own end-to-end deployment lifecycle for customer environments from bare hardware to running systems.
• Build and maintain Kubernetes deployments across on-premise environments.
• Develop GitOps workflows and automated reconciliation.
• Create IaC-based cloud infrastructure for dev and staging.
• Own CI/CD pipelines, builds, tests, deployments and releases.
• Deploy and optimise AI inference workloads on GPU hardware.
• Tune model serving infrastructure for performance and latency.
• Improve observability via monitoring, tracing and diagnostics.
• Secure systems for secrets, permissions and industrial networks.
• Produce documentation, runbooks and automated tooling.
• Identify opportunities to reduce manual work and improve efficiency.

Skills

Kubernetes

CI/CD

Linux

Python

GPU workloads

Observability

GitOps

Tools

Terraform

Docker

Flux/Argo CD

OpenTelemetry

Job description

We're partnering with an AI company transforming industrial environments through intelligent, on-premise AI systems. Their platform processes live operational data on customer hardware, delivering real-time insights for critical industries.

They're looking for an Infrastructure Engineer to own platform deployment, reliability and scaling across Kubernetes, GPU infrastructure and cloud environments. As an early engineer, you'll have significant ownership in shaping the architecture, tooling and future direction of the platform.

What You'll Do

• Own the end-to-end deployment lifecycle for customer environments, from bare hardware through to fully operational systems.
• Build and maintain Kubernetes-based deployments across single-node and multi-node on-premise environments.
• Develop reliable GitOps workflows, managing deployments through version-controlled infrastructure and automated reconciliation.
• Build and maintain cloud infrastructure for development and staging environments using Infrastructure as Code.
• Own CI/CD pipelines, including automated builds, testing workflows, deployment processes and release management.
• Deploy and optimise AI inference workloads running on customer GPU hardware.
• Configure and tune model serving infrastructure, balancing performance, latency and hardware constraints.
• Improve observability across applications, infrastructure and AI workloads through monitoring, tracing and diagnostics.
• Build secure systems for managing secrets, permissions and industrial network environments.
• Create documentation, runbooks and automation that make deployments repeatable and supportable.
• Identify opportunities to remove manual processes and improve engineering efficiency.

Who We’re Looking For

• Strong experience with Kubernetes, including troubleshooting production environments, networking, storage and cluster operations.
• Hands-on experience deploying Kubernetes outside managed cloud environments (e.g. k3s, RKE2, MicroK8s or similar).
• Production experience with Infrastructure as Code tools such as Terraform.
• Strong Docker experience, including multi-service applications, image optimisation and registry workflows.
• Experience owning CI/CD pipelines and improving software delivery processes.
• Experience running AI/ML workloads on GPU infrastructure, including model serving and performance optimisation.
• Understanding of GPU resources, including VRAM management, batching, quantisation and inference optimisation.
• Strong Linux and Bash skills, with the ability to work with Python-based applications.
• A first-principles approach to debugging complex technical issues.
• Strong ownership mindset and ability to operate independently in a fast-moving environment.

Nice To Have

• Experience with GitOps tools such as Flux or Argo CD.
• Background working with edge computing, air-gapped environments or customer-hosted infrastructure.
• Experience with industrial environments, manufacturing systems, PLCs or industrial protocols.
• Knowledge of GPU scheduling, multi-model inference or GPU sharing technologies.
• Experience managing databases such as PostgreSQL or time-series databases.
• Familiarity with observability tools such as OpenTelemetry or AI tracing platforms.

What Is In It For You?

• Opportunity to join an early-stage AI company solving complex real-world industrial challenges.
• High ownership and autonomy from day one, working directly with engineering leadership.
• Build infrastructure where the challenges go beyond traditional cloud environments.
• Work on cutting-edge AI systems running directly on physical hardware.
• Shape engineering practices, architecture and deployment strategy as the company scales.
• Exposure to complex problems across infrastructure, AI, hardware and software engineering.

Interested?

If you’re an Infrastructure Engineer who enjoys solving difficult engineering problems and wants to build the next generation of AI-powered industrial systems, we’d love to hear from you.