Platform Engineer | AI Infrastructure Specialist | 11+ Years Experience - Based in Seattle, available for async collaboration across time zones.
Core Services:
MCP Servers & AI Agent Infrastructure
I design and deploy Model Context Protocol (MCP) servers that enable AI agents to connect with external tools, databases, and APIs. My implementations include persistent context management, memory systems, and seamless integration with Claude, GPT, and open-source LLMs. I've built MCP servers running as Kubernetes services with vector storage backends for semantic retrieval.
Internal Chat Systems & LLM Gateways
I build enterprise chat platforms backed by Azure OpenAI and self-hosted LLMs. This includes LiteLLM gateway configuration for multi-model routing, authentication, rate limiting, and token management. I've deployed LibreChat on AKS with MongoDB, memory servers, and full observability — giving teams a private, secure alternative to consumer AI tools.
Supporting Expertise:

Kubernetes (AKS/EKS) with GitOps, KEDA autoscaling, workload identity
RAG pipelines with ChromaDB, vector databases, semantic search
Cross-cloud infrastructure (AWS & Azure)
Cost optimization — reduced platform costs by 40-60%

Certifications: CKAD • Azure DevOps Expert • AWS Solutions Architect
Available for part-time advisory, architecture reviews, and hands-on implementation.