Lead AI Platform Engineer working remotely from Indonesia with a Dubai-based team.
Where I've built
About
I talk to founders and client teams directly, then build the system and explain it back without the jargon.
Read my storyMore than 10 years in software and platform engineering
3 clouds shipped on, plus on-prem and air-gapped
90 percent less manual reconciliation
70 to 90 percent engineering productivity gain from shared platforms
A citizen asks one question and the right government service answers, without the citizen knowing which department that is.
Small companies got a shopping assistant for their customers, a private document assistant for their staff, and automated back-office routines, without hiring an AI team.
A government security team gets an assistant that reads every alert from every tool and tells them which ones matter, in plain language.
Customers can phone or speak to a service and get an answer in natural Arabic, without waiting for a human agent.
Instead of building features, I built the shared pieces every feature needed, once, properly.
Students got a chatbot that answered their questions during exam season, and it became the channel that brought in the most new students that year.
Experience
Capabilities
MCP tool callingA2A agent-to-agent protocolagent registry and intent routingRAG (Qdrant, pgvector, Bedrock Knowledge Bases)guardrails and confirmation gatesevaluation and tracing (Langfuse, Arize Phoenix)LangChaincontext engineering
Google Vertex AI (Gemini, tool calling)Amazon Bedrock (Knowledge Bases)Azure OpenAI / AI FoundryvLLMOllamaTGIKubeflowKServeMLflow
Google CloudAWSAzureon-premiseshybrid and air-gapped deploymentsmulti-environment rollouts with Helm and Kustomize
Kubernetes (Helm, Kustomize, bare-metal and on-prem clusters)Terraform (modular, multi-environment)DockerCI/CD pipelinesobservability and drift / latency dashboards
PostgreSQL (pgvector)MySQLBigQueryRedisElasticsearchKafkaGoogle Pub/SubChange Data CaptureOracle NetSuite (SuiteTalk REST, token-based auth)HubSpotWhatsApp Business API
Python (FastAPI, Flask)GoJavaJavaScript / ReactPHPCRESTgRPCOpenAPIWebSocket / WebRTC (LiveKit)Clean ArchitectureDDD
Ask my AI
Every answer shows its model, tokens, cache and cost.
Writing
Latest thought
Software engineers often look at AI and assume their experience is about to be replaced. It is not. Microservices and AI agent systems use the same two architecture patterns, orchestration and choreography. What changed is the actor: a service is deterministic, an agent is probabilistic, and every difference between the two worlds comes from that.
Updates
Talks
An LLM is not a system.
Publication
Kinematic Analysis of 7 DoF Head Humanoid FLoW: V-REP Simulation
If you are a founder with an AI idea and no engineer in the room yet, write to me. I will answer in plain words.
WIB (UTC+7) · working with a team in Dubai