Skills

Develop AI-powered applications using Genkit in Go.

Develop AI-powered applications using Genkit in Node.js/TypeScript.

Develop AI-powered applications using Genkit in Python.

Provides safety-critical validation, guardrails, and data reduction for gcloud CLI operations across Google Cloud Platform (GCP) services and infrastructure.

Manages custom Agent resources on Gemini Enterprise Agent Platform.

Guides the usage of Gemini Interactions API on Gemini Enterprise Agent Platform.

Generates a Gemini LiveAPI client service class in the user's chosen programming language.

Diagnoses, predicts, and mitigates node disruptions during Compute Engine host maintenance and hardware or software maintenance events for GPU and TPU…

Diagnoses GKE JobSet interruptions, restarts, and preemptions for AI/ML training workloads autonomously.

Diagnose and mitigate GKE TPU or GPU nodes stuck in NotReady / NodeStatusUnknown ("Kubelet stopped posting node status") due to host kernel panics, hardware…

Monitors, troubleshoots, and manages GKE TPU Dynamic Slices custom resources.

Monitors and troubleshoots GKE TPU workloads, nodes, and node pools using GKE system metrics and PromQL.

Diagnose GKE Cloud TPU multi-slice training hangs (Megascale `HANG_DETECTED` logs and hang monitored events) using the ML Diagnostics `Megascale XLA (MXLA)…

Diagnose and resolve GKE TPU slice creation failures (SliceCreationFailed) caused by partition overlap conflicts where requested TPU partitions or their nodes…

Diagnose GKE Cloud TPU training throughput drops and step-time regressions (15%+ TPU duty-cycle drop) using ML Diagnostics Workload Monitoring (`gcloud alpha…

Diagnose and resolve cluster-wide GKE TPU node pool creation or scale-up failures caused by Compute Engine reservation stockouts (GCE_STOCKOUT…

Diagnose and resolve GKE TPU Dynamic Slice creation and JobSet scheduling failures blocked by underlying Compute Engine managed instance groups (MIGs) stuck…

Diagnoses and prevents vbar_control_agent segfaults, out-of-memory (OOM) errors, and TPU device initialization failures on TPU v6e nodes in GKE caused by race…

Diagnose GKE TPU VM instances stuck in Compute Engine repair (REPAIRING state) after host errors, maintenance events, or faulty host reports in single-host…

Configures alerting policies in Terraform for Google Kubernetes Engine (GKE) clusters, workloads, and services using PromQL and Google Cloud Managed Service…

Manages GKE application onboarding, covering containerization, deployment manifests, and migration.

Manages core GKE cluster provisioning, credentials, Autopilot vs Standard selection, and workload deployment.

Runs batch and HPC workloads on GKE, utilizing job queues and parallel processing.

Trigger on mention of GKE cluster autoscaler, node autoscaling, node pool auto-creation / node auto-provisioning.