Platform Engineer, AI Infrastructure
Focused Labs•Denver, CO
•Hybrid
About The Position
Focused is hiring a Platform Engineer to help build an enterprise AI platform for a global enterprise client. The role works alongside a Senior Platform Engineer on Kubernetes and cloud foundations, while also supporting AI platform development, including model access, agent deployment, and helping application teams bring LLM workloads into production. The role is based in the Denver office three days per week and may require up to 20% travel within the United States. Focused is unable to sponsor or take over sponsorship of employment visas.
Requirements
- At least 5 years in platform, infrastructure, DevOps, or SRE roles.
- Hands-on production experience with Kubernetes.
- Experience with Azure and/or GCP.
- Experience with Terraform or similar infrastructure-as-code tools.
- Experience supporting AI/ML platforms or ML workloads in production.
- Proficiency in Python plus solid scripting skills.
Nice To Haves
- Experience building LLM applications or agents using LangChain, LangGraph, LlamaIndex, or similar.
- Experience with Azure OpenAI or Vertex AI.
- Familiarity with GPU infrastructure and model serving.
- Consulting or client-facing experience.
- Having shipped an LLM feature or agent to real users, rather than only producing a demo.
- Enjoying pairing and learning quickly from senior engineers.
- Building documentation systems that auto-update for the next person and coding agent.
Responsibilities
- Build and operate Kubernetes clusters on Azure AKS and GCP GKE.
- Write and maintain Terraform modules for cloud resources and environments.
- Build CI/CD and GitOps pipelines for platform and application deployments.
- Monitor, troubleshoot, and improve the reliability of AI/ML platform services.
- Deploy and operate supporting services for LLM applications, including model gateways, vector databases, tracing, and evaluation.
- Support GPU workloads, including node pools, scheduling, and cost monitoring.
- Write runbooks and automate day-two operations.
- Build reference agents and LLM application templates for client teams.
- Help application teams integrate with the platform and debug their workloads.
- Prototype with agent frameworks and LLM APIs to test platform requirements.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
Upload and Match Resume
What This Job Offers
Job Type
Full-time
Career Level
Mid Level
Education Level
No Education Listed
