Lead AI Enablement Engineer

Matrix is hiring a Lead AI Enablement Engineer to drive adoption of AI-assisted engineering practices across product teams. The role develops reusable AI workflows and agent integrations, strengthens validation and governance, and enables AI-powered product and internal capabilities while measuring engineering outcomes.

Responsibilities:

• Establish and scale AI-assisted workflows across the software development lifecycle, including planning, coding, debugging, testing, design, documentation, code reviews, and production investigation
• Develop reusable agent instructions, prompts, skills, repository context, integrations, and reference implementations that engineering teams can adopt directly
• Evaluate emerging AI coding tools, LLM platforms, and agent frameworks to identify opportunities to improve engineering productivity and software delivery
• Help teams transition from ad hoc, locally executed AI usage toward structured, repeatable, and validated AI-assisted workflows
• Partner with the Platform Lead to integrate AI workflows with CI/CD pipelines, automated testing, development sandboxes, observability, release readiness, and developer productivity tooling
• Develop patterns for orchestrating multiple AI agents and parallel workflows, with appropriate human oversight and validation
• Build integrations with developer tools, repositories, APIs, and internal systems to provide AI agents with relevant context and controlled access to resources
• Contribute to the evolution of sandbox-based agent execution environments that support safe, reliable, and scalable engineering workflows
• Design validation loops that ensure AI-generated code and other outputs meet engineering standards through automated tests, code reviews, security checks, and release controls
• Establish evaluation methods and quality signals to assess the accuracy, reliability, usefulness, and consistency of AI-assisted workflows
• Apply sound engineering judgment to security, privacy, access control, auditability, operational risk, and AI usage costs
• Collaborate with engineering and platform stakeholders to ensure AI adoption improves outcomes without compromising production reliability or software quality
• Define reusable architectural patterns for AI-powered product features and internal employee capabilities
• Support the development of AI assistants, retrieval-augmented generation (RAG) solutions, knowledge agents, workflow automation, and tool-enabled applications
• Establish shared patterns for agent integrations, context management, permissions, governance, and reusable AI components
• Partner with product and engineering teams to identify opportunities to embed AI into existing workflows and customer-facing capabilities
• Drive adoption through hands-on demonstrations, pairing sessions, workshops, documentation, examples, and engineering office hours
• Coach engineers on effective AI-assisted development practices, agent orchestration, and output validation
• Measure the impact of AI enablement using adoption, productivity, delivery speed, software quality, developer experience, and cost metrics
• Continuously refine workflows based on engineering feedback, evaluation results, and measurable business outcomes

Requirements:

• Significant practical experience using AI tools for real-world software engineering, including AI coding assistants, agentic development workflows, and LLM-powered developer tools
• Hands-on experience with tools such as Claude Code, Warp, or comparable AI coding and engineering platforms
• Strong software engineering fundamentals, including application development, testing, code review, debugging, and production support
• Experience building reusable developer workflows, integrations, automation, agent instructions, prompt patterns, skills, or reference implementations
• Working knowledge of LLM APIs, tool calling, agent orchestration, and Model Context Protocol (MCP) or comparable integration approaches
• Understanding of modern software delivery practices, including Git, CI/CD, automated testing, release management, and production readiness
• Ability to evaluate AI-generated outputs critically and implement appropriate testing, review, security, and validation mechanisms
• Strong communication and collaboration skills, with the ability to influence engineering practices and drive adoption across teams
• A practical, AI-first mindset focused on measurable improvements in engineering productivity, delivery quality, and developer experience
• Proficiency in at least one modern programming language, such as Python, TypeScript, Go, C#, or .NET
• Experience with several of the following technologies and capabilities is highly desirable:
• Experience implementing sandboxed or cloud-based agent execution and parallel AI workflows
• Familiarity with human-in-the-loop orchestration and validation of autonomous or semi-autonomous agents
• Experience building AI-powered SaaS features, internal knowledge-base agents, Slack integrations, or employee AI assistants
• Experience modernizing legacy applications or engineering workflows in a mature production SaaS environment
• Domain experience in fintech, payments, accounting, eCommerce, property management, or other transactional businesses
• Experience working in security-conscious, compliance-driven, or regulated environments
• 7+ years of software engineering experience preferred
• Claude Code, Warp, AI coding agents, and LLM-powered developer workflows
• Agent SDKs and APIs from Anthropic, OpenAI, AWS Bedrock, or comparable platforms
• MCP servers, tool calling, agent orchestration, reusable instructions, prompt engineering, and agent skills
• Git-based development workflows, CI/CD pipelines, test automation, code review, and release management
• Developer productivity platforms, internal tooling, and engineering workflow automation
• Retrieval-augmented generation (RAG), semantic search, embeddings, vector databases, and knowledge agents
• AI assistants, workflow automation, and integrations with internal systems and collaboration tools
• AWS or comparable cloud platforms, containers, and sandboxed execution environments
• Logging, tracing, monitoring, observability, AI evaluation, and cost tracking
• Security controls, identity and access management, privacy, auditability, and governance for AI systems