AI Platform Engineering Scaling Agentic AI, Serverless & Kubernetes
AI Platform Engineer Lead with 8+ years spanning AI/ML and cloud infrastructure across banking, fintech, healthcare, and manufacturing. Currently architecting production-grade AI Agent deployment systems on GCP, from serverless Cloud Run and GKE clusters to Terraform-managed IaC and CI/CD automation.
Explore More Insights
Dive deeper into my collection of articles covering MLOps, artificial intelligence, cloud infrastructure, and software engineering.
Routing AI Traffic: GKE Istio vs Cloud Run Load Balancers
Eliminating Dockerfiles with Cloud Native Buildpacks
Featured Projects
GKE GitOps Cluster Provisioning
Complete GitOps configuration for a Kubernetes AI platform — Istio ingress with VirtualService routing, Cert-Manager with private CA, ArgoCD self-healing sync, plus infrastructure for Qdrant, Dify, LiteLLM, and OpenTelemetry.
Cloud Run Infrastructure Automation
Terraform modules for provisioning Internal HTTPS Load Balancers with dynamic backend services, Serverless NEGs, URL Maps, SSL certificate rotation, and HTTP-to-HTTPS redirect — all driven by environment-specific tfvars files.
Enterprise AI Knowledge Base Platform
A FastAPI-based document retrieval and ingestion platform powering AI Agent RAG workflows. Features hybrid search (RRF combining BM25 + KNN), async ingestion via Pub/Sub and DocumentAI, neighbor-context enrichment, and multi-embedding support (Vertex AI, Qwen).