Rafael COELHO

Senior AI Engineer · Agentic AI, LLMOps & MLOps

Production AI systems on Kubernetes — from real-time incremental pipelines to adaptive agentic RAG.

Six years engineering production ML systems end to end — Kafka and Spark pipelines, full GitOps delivery. Architect of COELHO Nexus, a Kubernetes-native platform running three production agentic AI features on one self-learning LLM rotator, evaluation-gated pipelines, and full observability via LangFuse · OpenTelemetry · Alloy · LGTM — at $0 inference cost.

Delivered production ML/AI systems across government, financial markets, real estate, logistics, and cybersecurity.

Brazil Available · Senior AI / MLOps roles
Rafael Coelho

By the numbers

6+ yrs
production ML and Data Science engineering
9
public AI / ML projects shipped end-to-end
BSc
Mathematics · Federal University of Paraná (UFPR)

Selected work

All work →
COELHO Nexus logo

COELHO Nexus

Flagship
JUL 2026

Kubernetes-native multi-agent AI platform hosting three production features — documentation distillation, YouTube GraphRAG search, and autonomous research digests — on one shared LLM rotator, six data stores, and full GitOps observability, architected and operated solo.

Three AI features live on one platform · 124 REST endpoints across four domains · 18 Terraform modules across a 6-layer dependency graph · 20+ free-tier LLMs routed by a variance-aware Thompson-sampling bandit · dual observability (Grafana LGTM + LangFuse) on every call.
Kubernetes Terraform ArgoCD FastAPI FastHTML FastMCP +12 more
COELHO RealTime logo

COELHO RealTime

Flagship
JAN 2026

Production-grade Real-Time MLOps platform on Kubernetes combining incremental ML and batch ML across fraud detection, ETA prediction, and customer segmentation.

39 FastAPI endpoints across three versioned routers · sub-millisecond Redis-cached inference · end-to-end GitOps (Terraform → Helm → ArgoCD → GitLab CI) · full observability stack (Prometheus + Grafana + Alertmanager + Karma).
Kubernetes k3d Kafka Spark Delta Lake MinIO +16 more
YouTube Content Search logo

YouTube Content Search

MAR 2025

Multi-mode GraphRAG platform that extracts entities and relationships from YouTube transcripts into a Neo4j knowledge graph for multi-hop reasoning — the research that became COELHO Nexus.

Four search modes (Search · Video · Channel · Playlist) · multi-hop reasoning via Neo4j knowledge graph · multi-provider LLM routing across Groq, OpenAI, SambaNova, Scaleway.
LangChain LangGraph Neo4j GraphRAG Llama 3.1 Gemma 2 +6 more
COELHO Agents logo

COELHO Agents

FEB 2025

Multi-agent platform combining a memory-aware assistant, an autonomous Software Developer agent with self-fixing code loops, and a GraphRAG-based YouTube Content Search — all orchestrated with LangChain + LangGraph.

Three production agent tools shipped end-to-end · autonomous code-fix retry loops in the Software Developer · GraphRAG (Neo4j) backing multi-hop video query reasoning.
LangChain LangGraph Neo4j GraphRAG Streamlit Python +2 more

Recent writing

All writing →

Enterprise MLOps platform — production Kubernetes infrastructure with full CI/CD, GitOps, and workflow orchestration

DEC 3, 2025

Production-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.

#kubernetes #mlops #terraform #argocd

Building a local Kubernetes cluster and provisioning DevOps services with Terraform

NOV 10, 2025

How 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.

#kubernetes #k3d #terraform #helm