2. DevOps & Infrastructure

Diagnoses and resolves Kubernetes cluster issues through resource inspection, pod logs, and event analysis for efficient infrastructure management.

Assists in crafting Tempo trace queries, troubleshooting distributed traces, and correlating logs (Loki) and metrics (Mimir) for root cause analysis in distributed systems.

Automates React application building and SSH-based deployment to Hostinger for production environments.

Optimizes Prometheus and Mimir queries, troubleshoots metric issues, and prevents high-cardinality problems for efficient monitoring.

Troubleshoots Azure VMs, AKS, ACR, Storage, and Log Analytics using tool-first and CLI fallback.

Troubleshoot AWS infrastructure services including EKS, S3, EC2, networking, and IAM configurations using tool-first access.

Automates React application builds and SSH-based deployment to Hostinger for production releases.

Automates code quality verification, ensuring all gates are passed before code is deemed complete.

Troubleshoots GCP infrastructure services including Cloud Run, Firestore, networking, and storage via integrated tools with CLI fallback.

Automates deployment workflows for password generator web applications, including CI/CD setup and production environment preparation.

Executes PR merges with CI checks and context from Linear/GitHub, handling validation, polling, and status updates via command trigger.

Monitors CI/CD pipeline status for pull requests and provides error reporting for immediate issue resolution.

Deploys applications, models, and infrastructure to AWS services including SageMaker, Amplify, and EC2.

Syncs public assets (embeddings, index files) to and from S3 for deployment readiness. Ensures latest assets are available in cloud storage.

Enables remote management of tmux terminal sessions, allowing keystroke input and output scraping for interactive command-line tools like Python and GDB.

Manages Dockerized Apache Spark clusters for local and production environments with S3 integration. Start, stop, and check cluster status.

Manages AWS EC2 instances for GPU workloads and Spark jobs, enabling start, stop, and status checks via command.

Automates two-phase code synchronization from development branches to main, preventing conflicts and ensuring CI reconciliation after production validation.

Runs and summarizes code change tests within CI/CD pipelines, specifically in Build and Gate stages.

Enables command-line interaction with Azure DevOps for managing work items, pull requests, and repositories.

Automates software release workflow: merges branches, bumps versions, publishes to npm, and creates GitHub releases.

Automates migration of Azure resources including PostgreSQL databases, Storage Accounts, and Container Registry images across subscriptions and regions.

Provides real-time analytics and performance metrics for minion services, including success rates, latency, and session history.

Verifies Ollama service status and model configuration to diagnose and resolve minion-related operational issues.