Ai Infrastructure Devops Engineer

Secure and operate AI infrastructure at Terawatt Infrastructure, combining DevOps leadership with cloud reliability, observability, and agentic systems expertise.As a Staff DevOps Engineer, you will own infrastructure supporting Terawatt’s internal tools and AI platform. You will partner with the AI Product Manager and engineers to deploy, secure, observe, and scale agentic workflows. The role also supports charging infrastructure through production cloud platforms, data systems, and incident response.Key Responsibilities:
Operate infrastructure for ML and internal AI workloadsExtend security controls across AI and agentic systemsAutomate SOC 2 compliance controls and vulnerability detectionBuild container-based development and production-like testing environmentsSupport multi-service observability with OpenTelemetry and Grafana CloudRequirements:
8+ years operating high-availability production systemsExperience leading SRE or DevOps initiativesExperience with AWS, EKS, and TerraformExperience operating LLM applications or agents preferredStrong communication across technical and product teamsLead secure AI infrastructure and dependable DevOps practices across Terawatt’s charging network and internal technology platforms.
#J-18808-Ljbffr