AI Enablement

My interest in AI grew organically from my work in developer relations. As a leader focused on developer experience, community, and tooling, I saw firsthand how AI was changing the way developers build, automate, and interact with systems.

Exploring AI at Cisco

During my time as Senior Manager of Developer Advocacy at Cisco, I worked with my team to explore how AI could impact developers using Cisco platforms. We focused on three key areas:

• Developer Tooling: I incorporated AI into my own workflows, using vibe coding to prototype solutions and embedded AI tools for document editing and content acceleration.
• Network Infrastructure: We explored how AI impacts bandwidth, security, and adaptability of developer-accessible networks.
• Agentic AI and Network Automation: The most exciting frontier was AI-powered network automation. DevNet always prioritized automation, but with AI, networks could proactively adapt and manage themselves, transforming how developers build and operate.

Post-Cisco AI Enablement & Consulting

After Cisco, I consulted on community engagement and AI enablement. My AI-focused projects included:

• NTTV Chatbot — Deterministic RAG Assistant: I built a lightweight chatbot using retrieval-augmented generation, deterministic extractors, FAISS retrieval, and LLM routing to deliver grounded answers with low infrastructure overhead. View on GitHub.
• Music Scout — Agent Memory Demo: I built an AI agent that scouts for emerging artists, maintains transparent JSON-based memory, tracks provenance, deduplicates discoveries, and uses a local LLM for bounded enrichment. View on GitHub.
• Pedalboard Extractor — Structured Extraction Demo: I built a demo that turns messy guitar pedal notes into structured records, uses deterministic filtering for natural-language constraints, and optionally uses a local LLM as a grounded narration layer. View on GitHub.
• Custom GPT for Targeted Content Generation: I developed a custom GPT that creates content tailored to specific prompts, topics, and personas.

I wrote about my experience with the LLM and the importance of solid content in the article below:

Uber & Michelangelo: Open-Source MLOps

In my contract with Uber, I help build, support, and grow the developer community for Michelangelo, Uber's open-source machine-learning platform. As an individual contributor Developer Advocate, I connect developers with the tools, knowledge, and support they need to adopt the platform and contribute to its development.

Michelangelo brings experience operating machine learning at Uber's scale to the wider community. Its open-source approach creates a shared foundation for machine-learning operations (MLOps), with reusable Kubernetes operators and common workflows for training and serving models. By helping teams standardize how they run ML workloads and manage infrastructure, it reduces duplicated effort and makes it easier to move from experiments to production at scale.

My work spans the practical foundations of an open-source developer community:

• Community engagement: Build and manage forums, Slack, and email channels, with processes for engagement, moderation, and growth.
• Developer content and support: Create developer-focused resources and work directly with the Michelangelo AI community to help people get started and build with the platform.
• Repository operations: Review pull requests, triage issues, and develop processes for request for comments (RFC) approval and feature tracking.
• Industry events: Represent the project at Kubernetes Community Day San Francisco Bay Area 2026 and WeAreDevelopers World Congress North America 2026.

Why This Matters

AI is changing how developers work, how networks function, and how communities engage. My focus has always been on enabling people in technology to succeed, and AI is now a core part of that mission. Whether it’s creating smarter support systems, simplifying complex workflows, or scaling community efforts, I’m excited about the possibilities AI brings to developer ecosystems.