AI-Native Cloud & DevSecOps Engineer focused on multi-cloud platforms, Kubernetes, Infrastructure as Code, GitOps, secure delivery, observability, and AI agents.
| Area | Enterprise focus |
|---|---|
| AI & Agents | OpenAI Agents SDK, LangGraph, MCP, RAG, tool use, guardrails, evaluation and production automation |
| Cloud Platforms | AWS, Azure, GCP, Kubernetes, Crossplane, Backstage and scalable internal developer platforms |
| DevSecOps & GitOps | Secure CI/CD, OpenTofu/Terraform, policy as code, signed artifacts and supply-chain security |
| Reliability | SRE, OpenTelemetry, eBPF observability, SLOs, incident readiness and FinOps |
I turn business outcomes into secure, repeatable platforms—with automation, governance, and operational feedback built into the delivery path.
AI & Application Engineering
Cloud & Platform
Delivery, Security & Operations
Agentic AI & LLMOps
Platform Engineering & Cloud Native
Policy, Identity & Software Supply Chain
Observability, SRE & FinOps
End-to-end operating model: define measurable value → design architecture and controls → codify applications and infrastructure → verify quality and security → release through governed automation → operate against SLOs → feed production learning into the next decision.
| Project | What it demonstrates | Core technologies |
|---|---|---|
| ChurnCue → | Production-oriented customer-retention intelligence with deterministic ML, governed MCP tools, and human approval boundaries | Python, scikit-learn, MCP, Docker |
| CreatorOps AI → | End-to-end idea-to-video system spanning structured scripts, authorized voice, AI visuals, subtitles, and HD rendering | Next.js, FastAPI, OpenAI, FFmpeg |
| AI Engineer Roadmap → | Project-based progression from Cloud/DevOps into AI engineering, agents, RAG, LLMOps, and MLOps | Python, RAG, MCP, Kubernetes, Terraform |
