Senior Platform Engineer | Backend, DevOps & AWS Infrastructure | LLM Systems in Production | AI Agents & Automation | Python, TypeScript, Terraform | 37K+ YouTube Subs (@CodeWithMuh)
I build and deploy production-ready AI applications — combining LLMs, backend engineering, and cloud infrastructure to turn ideas into reliable systems.
- LLM-powered applications: Integrate and deploy models from OpenAI, Anthropic, and open-source ecosystems.
- AI agents & automation: Build tool-using agents, workflow automation, and AI voice experiences.
- RAG & document AI: Develop retrieval-augmented generation, document processing, and knowledge-based systems.
- Production AI infrastructure: Deploy, scale, monitor, and optimize AI workloads on cloud platforms.
- Backend & APIs: Build reliable services with Python, Django, Django REST Framework, and FastAPI.
- Cloud & DevOps: Automate infrastructure and delivery with AWS, Docker, Terraform, and CI/CD.
Explore 65+ open-source, production-grade repositories featuring native Mermaid architecture diagrams, zero-secret hygiene, and official SemVer releases:
| Project | Highlights & Tech Stack | Release |
|---|---|---|
aws-eks-ha-platform |
High-availability AWS EKS Platform with ArgoCD GitOps, Helm, Karpenter & Valkey |  |
three-tier-devsecops-project |
End-to-end DevSecOps pipeline with Jenkins, SonarQube, Trivy, Docker & K8s | |
kessai-payments |
Multi-region resilient payments platform on AWS EKS with Chaos Engineering | |
01_devops-aws-terraform-ecs |
Automated AWS Terraform IaC provisioning: Multi-AZ VPC, ECS Fargate, RDS & ALB | |
django-aws-ecs-terraform |
Serverless container deployment with Terraform, ECS Fargate & CloudWatch | |
redshift |
Terraform-automated Amazon Redshift OLAP Data Warehouse with S3 integration | |
| Project | Highlights & Tech Stack | Release |
|---|---|---|
ai-voice-agent |
Real-time interactive AI Voice Agent with Twilio WebSockets, Claude 3.5 & FastAPI | |
private-llm-chat-sagemaker-aws |
Self-hosted enterprise LLM platform powered by vLLM on AWS SageMaker GPUs | |
private-llm-chat-cloudrun-gcp |
Serverless private LLM inference chat system on Google Cloud Run with GPUs | |
ai-support-agent |
Autonomous customer support agent with RAG, pgvector embeddings & Next.js UI | |
shopagent |
E-commerce conversational sales agent utilizing Claude function-calling tools | |
mlops |
End-to-end MLOps pipeline: MLflow tracking, DVC versioning, EKS serving & drift monitoring | |
| Project | Highlights & Tech Stack | Release |
|---|---|---|
system-design |
Comprehensive visual architecture framework: microservices, caching, sharding & scalability | |
linux-course |
5-phase Linux DevOps curriculum: shell scripting, sysadmin, systemd & networking | |
python-tutorial-for-beginners |
16-module progressive Python course: syntax, data structures, OOP & exception handling | |
django-signals-codewithmuh |
Architectural guide & implementation for decoupled event-driven Django model signals | |
ci-cd-configurations-files |
Curated production AWS CodePipeline, CodeBuild, CodeDeploy & runner definitions | |
Focus areas: LLM APIs · Open-source LLMs · Prompt Engineering · RAG · Embeddings · Vector Search · AI Agents · Tool Calling · Model Serving · Inference Optimization · LLM Evaluation
