Open to Senior / Staff Engineer and AI Engineering roles — remote, Americas or EMEA

I optimize for impact: team, problem, and growth trajectory over titles. I’ve consistently grown from mid-level to Tech Lead — and continue to operate at that trajectory.

I am a Tech Lead and Senior Software Engineer focused on turning real-world systems into AI-ready platforms. With 20 years of remote experience, I bridge scalable backend architecture with practical AI integrations — not as a feature, but as part of the system design.

Formerly at Dealerware — led a cross-functional squad of backend, QA, mobile, and frontend engineers; authored RFCs and ADRs; owned system architecture; and stayed close to the codebase. Delivered 370+ merged pull requests over four years on systems processing 10,000+ transactions per hour.

Built that foundation pre-AI, and now extend it by operationalizing AI into engineering workflows — applying structured approaches to prompt design, context management, and token efficiency to improve both developer productivity and system quality.

My current focus is AI Engineering — building systems, not demos. I design integrations, agent-based workflows, and supporting infrastructure that make LLMs reliable in real engineering environments. Beyond MCP and RAG, I focus on multi-step workflows and Spec-Driven Development to improve reliability, reduce ambiguity, and raise the quality of the software development lifecycle.

• AI-ready Rails systems (context + introspection)
• Agent-based engineering workflows (PRD → PR)
• Infrastructure to make LLMs reliable in production

→ Turning AI from a tool into a system

High-fidelity evaluation engine for benchmarking AI agent skills across any stack (Rails-first, but extensible).

The "ROI of Context" measurement tool. Compare baseline vs. skill-enhanced agent runs with 100% reproducibility via isolated Git sandboxes. LLM-based blind judging across Correctness, Skill Adherence, Code Quality, Test Coverage, and Documentation.

• Side-by-Side Evaluation: Quantify the impact of specific context or skills on agent performance.
• Isolated Git Sandboxes: Clean diffs, zero side-effects, and 100% reproducibility for every run.
• Multi-Provider: Native support for Anthropic, Gemini, OpenAI, DeepSeek, Groq, Ollama, and more.

gem install ruby-skill-bench

Turn any Rails app into an AI-ready codebase — one command, zero config.

The problem: AI assistants guess your app structure, waste tokens exploring it, and still produce generic or incorrect outputs. rails-ai-bridge fixes this at the root — giving AI tools structured, accurate context of your Rails app before the conversation even starts.

Two modes:

• rails ai:bridge — generates static context files committed to your repo (CLAUDE.md, AGENTS.md, .cursorrules, copilot-instructions.md, .windsurfrules, .mcp.json). No server needed. Whole team benefits automatically.
• rails ai:serve — live MCP server for real-time Rails introspection on demand.

gem 'rails-ai-bridge'
rails generate rails_ai_bridge:install
rails ai:bridge

Works with Antigravity · Claude Code · Codex · Cursor · Gemini · GitHub Copilot · Windsurf

Curated AI agent skill library for Ruby on Rails development.

Structured SKILL.md files that turn coding agents into disciplined Rails contributors — encoding context, conventions, and workflows with TDD as a hard gate and full chaining from PRD → PR.

Compatible with Antigravity · Claude Code · Codex · Cursor · Gemini · GitHub Copilot · Windsurf

• Designing agent-based engineering systems and integrating them into CI/CD feedback loops
• Preparing for the AI Engineer for Developers Associate Certification
• Writing about technical leadership and AI Engineering on Medium

Core

AI & Tooling

Architecture

• 🏅 Generative AI Fundamentals — Databricks Academy Accreditation
• 🤖 AI Agents in LangGraph — DeepLearning.AI
• 🤖 Building Agentic AI Systems — DeepLearning.AI
• 🛤 Advanced Product Management: Vision, Strategy & Metrics — LinkedIn Learning