Senior Engineer, AI Tooling & Developer Productivity

Moon•Glendale, CA

About The Position

This role is a force multiplier, focusing on shipping product features while fundamentally changing how the entire engineering team works. The engineer will own, extend, and evolve the company’s proprietary AI toolkit and lead a company-wide SDLC rebuild powered by AI agents. Responsibilities include mentoring a distributed offshore team on AI tool usage, designing the AI infrastructure for the engineering organization, and building AI-powered features directly into the home services SaaS product. The ideal candidate has a proven track record of changing team workflows, not just personal AI tool usage, with the goal of achieving 10x engineering productivity.

Requirements

Demonstrated experience driving AI tooling adoption across an engineering team — with measurable outcomes, not just personal usage.
Deep proficiency with AI-assisted coding tools like Cursor, GitHub Copilot, Claude Code, etc. — you use these daily, not occasionally.
Experience building and evolving AI agent systems: agent definitions, multi-agent orchestration, routing logic, and failure mode analysis.
Enough .NET / C# fluency to be credible and effective with a senior engineering team — you can review their code and spot issues.
TypeScript / Capacitor for frontend and cross-platform mobile work — you own the full stack for AI-powered features.
Experience integrating LLM APIs into production applications (OpenAI, Anthropic / Claude, Azure OpenAI, or similar).
Understanding of Model Context Protocol (MCP) — configuring servers, managing tool access, and troubleshooting integration issues.
Strong code review skills and the ability to set engineering standards that others follow.
Comfortable working with ambiguity — you can take a vague requirement and turn it into a well-scoped engineering task.

Nice To Haves

Experience with RAG (Retrieval-Augmented Generation) patterns or advanced AI agent workflow design.
Background in home services, field service management, or similar SaaS verticals.
Experienced with prompt engineering and AI workflow design beyond code generation.
Prior experience building Claude Code agents, skills, or custom workflows.

Responsibilities

Own, maintain, and continuously evolve the company’s Moon AI Toolkit.
Build new agents from scratch, defining scope, system prompts, tool access, and evaluation criteria.
Write new skills (e.g., Claude Code native skills) that are automatically discovered and invoked across the engineering workflow.
Design new multi-agent workflows that orchestrate specialists in parallel and sequentially to complete complex engineering tasks.
Maintain and improve the agent routing system, ensuring the right agent is dispatched for every task type, with clear escalation paths.
Evaluate agent performance continuously, identifying failure modes, rewriting underperforming agents, and logging learnings to the shared knowledge base.
Lead the redesign of the company’s SDLC using AI skills and agents as the primary mechanism of change.
Automate or AI-augment every repeatable SDLC step: ticket refinement, code review, test generation, documentation, and deployment verification.
Work directly with the engineering team to roll out changes company-wide, including training, change management, and feedback loops.
Define the measurable productivity baseline and track progress against the stated 10x improvement goal.
Own the rollout roadmap: from POC phase (first 90 days) through team-wide adoption.
Work across the .NET / C# backend (ASP.NET, EF Core), Python, TypeScript / Capacitor frontend (cross-platform mobile), and AI integration layer (LLM APIs, RAG, agent pipelines).
Build AI-powered features into the product directly, focusing on home services use cases including scheduling intelligence, recommendations, and workflow automation.
Maintain production quality throughout: tests, documentation, and code review for every feature shipped.
Design and implement the infrastructure and tooling environment that makes successful AI usage possible across all engineers.
Own MCP (Model Context Protocol) server configuration and management — the integration layer connecting AI agents to internal systems (Jira, Confluence, GitHub, Slack, Notion).
Standardize IDE plugin configuration and AI assistant settings across the team.
Design and maintain context injection pipelines — ensuring AI agents have access to accurate, up-to-date project context at all times.
Own the onboarding program for new engineers joining the AI-assisted workflow.
Implement engineering org-wide context layer best practices: structured context files (.claude/docs/ — project-map, known-issues, conventions, decisions, lessons), shared knowledge management, and AI tool configuration standards.
Own the prompt library governance process — curate, version-control, and share high-value prompts across the team.
Establish standards for how agents consume context: what goes in knowledge files, how to structure agent instructions, and how to keep context current as the codebase evolves.
Mentor and upskill engineers on AI tooling.
Define and roll out AI-assisted development standards across the whole engineering team (e.g., Cursor, Copilot, or equivalent).
Establish code quality standards and review practices that scale with AI-assisted development.
Help translate poorly defined or ambiguous tickets into clear, executable engineering tasks before work begins.