I'm a software engineer focused on building AI-powered systems — the kind that do real work autonomously. That means designing agent pipelines with multi-step reasoning, wiring tools and APIs into LLM workflows via MCP and LangGraph, and building the backend infrastructure that keeps it all running reliably in production.
My development stack is Python-first: FastAPI backends, async task queues, REST API design, PostgreSQL, and Redis. I've integrated AI at the API level across multiple providers — Anthropic, Google Vertex AI, and locally-hosted models via Ollama and LM Studio — and I understand how to move beyond basic prompting into context engineering, retrieval-augmented generation, and persistent memory architectures with vector and graph databases.
I also hold an uncommon advantage for a software engineer: I can take a project from code all the way through production deployment on infrastructure I built myself. My homelab runs a production private cloud — Proxmox hypervisor, GPU passthrough for local LLM inference, container orchestration, full observability stack — automated end-to-end with Terraform and Ansible. I learn by shipping things that actually run.
IBM Back-End Development Professional Certificate. PCEP Python certification. Completing BS Computer Science. Google Cloud Professional Architect in progress.
AI-First
Agent pipelines, RAG, MCP, LangGraph, multi-provider LLM integration
Full-Stack
Python · FastAPI · REST APIs · PostgreSQL · async workflows
Deployed
Self-hosted LLM inference, production cloud infra, GPU-accelerated AI stack
IaC
Terraform + Ansible automation from bare metal to running service
