I build cloud-native systems engineered for scale, reliability, and security — with a strong focus on AI infrastructure and DevSecOps.

Working across Kubernetes, Terraform, CI/CD, cloud platforms,Agentic Systems. I translate complex ideas into production-grade systems designed for real-world workloads.

Currently exploring the intersection of security, AI systems, and distributed cloud infrastructure, where resilience and intelligence converge with optimal resource utilisation.

• Cloud-native system architecture
• AI infrastructure engineering
• Secure software supply chains
• Observability, reliability, and runtime resilience

🤖 KubeOps-AI — Agentic AI for Kubernetes Operations

Cloud-native autonomous system for Kubernetes troubleshooting using local AI, observability tools, and secure execution pipelines.

It analyzes cluster issues, reasons about root causes, and safely suggests remediations through a human-approved workflow.

🧠 Core Workflow

• Detects issues using K8sGPT
• Reasons with local LLMs (Ollama + Gemma)
• Retrieves historical incidents via ChromaDB
• Generates safe kubectl remediation commands
• Executes only after human approval via dashboard

⚙️ Architecture

Frontend: React + Vite (Nginx-served dashboard)
Backend: FastAPI orchestration layer (agent-based system)
AI Layer: Ollama (local inference) , Gemma:2b Memory: ChromaDB (incident recall + context)
Tools: K8sGPT + kubectl execution engine

🛡️ Safety Model

• Guardrails prevent destructive operations
• Human-in-the-loop approval before execution
• Fully local inference (no external AI APIs)
• RBAC-based cluster access control
• Auditability via stored incident history

📌 Focus Areas

• Agentic AI for infrastructure operations
• Local LLM deployment in Kubernetes
• Memory-augmented troubleshooting systems
• Cloud-native AI system design (GKE / K3s)

🔗 Repository
https://github.com/barbaria888/KubeOps-AI

A cloud-native backend system for AI inference, designed for scalability, reliability, and real-time interaction.

• 🔄 WebSocket-based streaming API for real-time LLM responses
• 🧠 CPU-based LLM inference using Ollama (TinyLlama)
• 🌐 Kubernetes service discovery and internal networking
• ⚙️ CI/CD-driven Docker build and deployment pipeline
• 🛠️ Deep debugging across containers, networking, and runtime layers

A production-grade DevSecOps + GitOps pipeline with strong security and quality enforcement.

• 🔍 Code Security — CodeQL (SAST): Detects vulnerabilities (injection, secrets, auth flaws, etc.)
• 🧹 Linting — Code Quality Gate: Enforces clean, maintainable code
• 🧪 Automated Tests: Prevents regressions across services
• 🐳 Docker Build: Secure, reproducible container builds
• 🛡️ Container Security — Trivy Scan: Detects OS/package vulnerabilities & CVEs
• 📦 Artifact Distribution: Pushes verified images to Docker Hub

• Security embedded into CI/CD pipelines
• Shift-left vulnerability detection
• Secure software supply chain (SCA + SBOM)
• GitOps-based deployments with declarative control
• End-to-end pipeline gating for production readiness

• ☁️ Deploying AI workloads on cloud (GCP focus)
• ⚡ Exploring GPU vs CPU inference tradeoffs
• 🔐 Strengthening runtime and API security layers
• 🚀 Moving toward fully automated, scalable AI platforms

🔗 Repositories:
👉 https://github.com/barbaria888/Ollama-Chatbot-deployment
👉 https://github.com/barbaria888/Educonnect-D

• 🏗️ Google Cloud – Architecting with GKE, Terraform, AI Infrastructure (in progress)
• 🔐 IBM – Application Security for Devs & DevOps (in progress)
• 🧱 AWS – Cloud Essentials & Practitioner Prep
• 🧿 Oracle Cloud – OCI Foundations Associate
• 🦋 CNCF Stack – Kubernetes, Argo CD, OpenShift, Tekton

🎓 Continuous learning through hands-on labs, real systems, and applied projects—not just coursework.

“The number 1 skill set is flexibility and just knowing how things work and map that to real-world context … and that makes you clever.” — Kelsey Hightower

OBSERVE IN SILENCE · BUILD IN DEPTH · STRIKE WITH PRECISION

Engineered beneath the surface. Proven where it matters.