Senior AI Engineer · MLOps & Agentic Systems
Production AI systems on Kubernetes — from real-time incremental pipelines to adaptive agentic RAG.
Six years engineering production ML systems — Kafka, Spark, end-to-end GitOps. Architect of COELHO Nexus on Docker · Kubernetes · Helm · Terraform · Terragrunt — adaptive Agentic RAG with a multi-provider Thompson-sampling LLM rotator, two-stage retrieval, GraphRAG via Neo4j, and full observability via LangFuse · OpenTelemetry · Alloy · LGTM.
By the numbers
Selected work
All work →COELHO Nexus
FlagshipAgentic RAG + GraphRAG search platform that unlocks semantic search over YouTube transcripts — built solo, deployed for $0/month on Oracle Free Tier.
COELHO RealTime
FlagshipProduction-grade Real-Time MLOps platform on Kubernetes combining incremental ML and batch ML across fraud detection, ETA prediction, and customer segmentation.
Recent writing
All writing →Enterprise MLOps platform — production Kubernetes infrastructure with full CI/CD, GitOps, and workflow orchestration
DEC 3, 2025Production-grade MLOps platform on Kubernetes — Terraform, k3d, GitLab, ArgoCD, Apache Airflow, MinIO, Rancher — with end-to-end IaC, GitOps continuous delivery, and DAG-orchestrated ML pipelines. Validated against a Real-Time ML project.
Building a local Kubernetes cluster and provisioning DevOps services with Terraform
NOV 10, 2025How to build a local k3d cluster that hosts GitLab, Rancher, ArgoCD, and LocalStack — fully provisioned with Terraform for cross-OS reproducibility, with a complete CI/CD flow disposable in one terraform destroy.