Justin Cook jhcook

Hi there 👋

Engineering Leader • Distributed Systems • Agentic AI • Reliability & Automation • Telemetry & Visibility

I design and operate large-scale distributed systems and build the automation ecosystems that keep them reliable, observable, and fast. My work blends 30 years of hands-on engineering with a growing focus on agentic AI, Kubernetes platform engineering, and intelligent automation pipelines.

I’ve led global engineering teams across the US, UK, Russia, and Australia, delivering cloud-native transformations, SRE programs, and high-availability platforms for finance, energy, SaaS, and government.

My current obsession: building systems that reason about their own state and augment human operators, instead of just automating tasks.

🚀 Current Focus Areas

Distributed Systems Engineering
- Kubernetes, AWS, multi-cluster architectures, IaC, reliability tooling, observability design.
Agentic AI & Automation
- Multi-agent frameworks, RAG systems, telemetry-aware LLMs, AI-driven operational workflows, custom GPT tooling.
Platform Modernisation
- CI/CD transformations, cloud migration strategy, zero-downtime data upgrades, threat-aware network design.
SRE & Operational Excellence
- Incident automation, resiliency patterns, governance, cross-team enablement.

🧩 Featured Projects

🔹 Agentic Dev A framework for managing the lifecycle of agentic software development. It solves the "blank page" problem by providing structured planning, coding, and review workflows for autonomous agents. 👉 https://github.com/jhcook/agentic-dev

🔹 Agentic RAG A fast, practical RAG stack for structured retrieval and agent orchestration. Includes vector stores, indexing, REST/MCP servers, and multi-agent routing. 👉 https://github.com/jhcook/agentic-rag

🔹 Agentic AI A toolkit for building operational and voice-driven agents. Features Whisper transcription, LLM integration, structured logs, and CLI agent workflows. 👉 https://github.com/jhcook/agentic-ai

🔹 Kubernetes Dev Env A full-stack, reproducible Kubernetes development environment. Multi-runtime support (Minikube, Rancher Desktop), Calico networking, Prometheus/Grafana, and local GitOps patterns. 👉 https://github.com/jhcook/kubernetes-dev-env

🔹 Image to Video A media-AI pipeline supporting Sora-2, Azure Sora, Google Veo, and RunwayML. Prompt → video workflows with automated stitching and output controls. 👉 https://github.com/jhcook/image_to_video

🛠️ Languages & Tools

Cloud & Platforms: AWS, Kubernetes (EKS/OpenShift), Terraform, GitHub Actions
Languages: Python, Go, Shell
AI Tooling: OpenAI, CoPilot, Claude, Gemini, LangChain, LangGraph, MCP
Observability: Prometheus, Grafana, Datadog
Automation: Ansible, IaC frameworks, event-driven ops

🌏 Background in Brief

I’ve built and led engineering teams for finance, energy, and government; delivered global cloud-native transformations; enforced high-stakes compliance (SOC2, NERC CIP); and architected platforms trusted by millions of users. I enjoy the intersection where system architecture, leadership, and intelligent automation collide.