Senior Platform Engineer, AI Infrastructure

Focused•Denver, CO

1d•$180,000 - $220,000•Hybrid

About The Position

Focused is hiring a Senior Platform Engineer to lead the build-out of an enterprise AI platform for a global enterprise client. The engineer will design the foundation for teams to build and ship LLM applications and agents, covering Kubernetes, GPU capacity, security, and operational guardrails. The role sets technical direction and mentors a Platform Engineer working on the engagement. The position involves designing a multi-tenant platform for LLM and agentic AI workloads; architecting GPU infrastructure for inference and fine-tuning; establishing shared agent services; and making build-versus-buy recommendations. It also includes production Kubernetes and cloud infrastructure across Azure AKS and GCP GKE, Terraform and infrastructure-as-code standards, CI/CD and GitOps, and security and governance for AI workloads. The engineer will lead architecture reviews, document decisions, work with security and compliance teams, and build trusted relationships with client engineering leaders so the client team can operate the delivered platform. The role requires working from the Denver office three days per week and up to 20% travel within the United States. Focused is unable to sponsor or take over sponsorship of employment visas at this time. The Denver base salary range is $180,000–$220,000.

Requirements

At least 10 years of experience in infrastructure, platform, or DevOps engineering.
Deep production experience with Kubernetes, including Azure AKS.
Hands-on experience with GCP.
Expert-level Terraform experience.
Experience running GPU infrastructure, such as NVIDIA GPU Operator, node pools, and scheduling, or similar.
Experience building infrastructure that supports production LLM workloads.
Strong cloud security background, including IAM, networking, secrets, and policy as code.
Experience leading technical direction for a team.

Nice To Haves

Experience building an internal agentic AI platform.
Familiarity with model serving technologies such as vLLM, Triton, KServe, or Ray Serve.
Experience with Azure OpenAI or Vertex AI.
Consulting or client-facing experience.
Evidence of having built a platform adopted by other engineering teams.
Experience meaningfully reducing GPU spend without slowing teams down.
Ability to explain platform architecture to audiences ranging from CTOs to junior engineers.

Responsibilities

Design and build a multi-tenant platform for LLM and agentic AI workloads, from model access through deployment.
Architect GPU infrastructure for inference and fine-tuning, including scheduling, autoscaling, and cost controls.
Establish shared services for agents, including model gateways, secrets, tracing, evaluation, and deployment pipelines.
Make build-versus-buy decisions and explain tradeoffs to technical and executive stakeholders.
Architect and operate production Kubernetes on Azure AKS and GCP GKE.
Own Terraform modules and infrastructure-as-code standards across environments.
Build CI/CD and GitOps workflows to make platform changes safe and repeatable.
Design identity, network isolation, and secrets management for AI workloads.
Implement guardrails for data access, model usage, and auditability.
Partner with security and compliance teams to meet enterprise requirements.
Mentor and direct a Platform Engineer on the engagement.
Lead architecture reviews and write decision records.
Build trust with client engineering leaders and leave their team able to operate the platform.
Set technical direction for the platform and engagement.