AI Enablement Engineer

Topgolf•Dallas, TX

About The Position

The AI Enablement Engineer helps teams across Topgolf, technical and non-technical alike, get real value from AI by removing the friction that blocks adoption and building the reusable archetypes, skills, and governed integrations that let business teams build safe, working applications through Topgolf’s AI-SDLC pipeline. This role acts as the technical backstop, reviewing AI-generated code and specs for correctness, security, and adherence to engineering standards before anything ships. Partner with teams across Topgolf, technical and non-technical, to unblock AI adoption by configuring agent access, resolving friction, and showing teams how to get real value from available AI tools Design and build archetypes and skills (e.g., SKILL.md files, intake questionnaires, spec templates, code scaffolds) that package engineering standards and governance into reusable building blocks for the AI-SDLC pipeline Connect agents to internal systems, data sources, and tools through governed connectors and MCP-style integrations Monitor archetypes and agents for model drift, prompt bloat, and other degradation as underlying models and usage evolve, and keep code scaffolds and prompts current with secure coding practices and platform engineering standards Review AI agent-produced code, specs, and gate results for correctness, security, scope adherence, and good development practice before production Test archetypes and agents against adversarial prompting (prompt injection, jailbreak attempts) and implement guardrail hooks to enforce scope, safety, and policy compliance Build documentation, examples, and light training (office hours, walkthroughs, guides) to raise teams' baseline capability with AI Retire, merge, or extend archetypes based on usage and escalation patterns, and triage escalations to security, data owners, or app stewards, partnering with platform engineering so new archetypes and integrations fit the pipeline's runtime and release mechanics Triage escalations and route findings to security, data owners, or app stewards, following the pipeline's escalation rules. Partner with the platform engineering team so new archetypes and integrations fit the pipeline's constrained runtime, connector catalog, and release mechanics.

Requirements

Bachelor's degree in Computer Science, Engineering, or a related field, or equivalent practical experience.
3+ years of professional software engineering experience, with strong proficiency in Python and working knowledge of at least one other widely used language such as Go, TypeScript, or Java.
Strong grounding in core software development principles: automated testing, version control, code review, secure coding practices, and API design.
Hands on experience with LLM agent tooling, for example Claude Code, MCP, LangGraph, or a comparable framework, including prompting, tool use, and agent orchestration.
Experience with retrieval-augmented generation (RAG) and vector databases, and judgment for when they are the right tool versus a simpler approach.
Ability to evaluate AI generated code for correctness and risk, and to explain technical tradeoffs to non-technical stakeholders in plain language.
Experience designing templates, documentation, or tooling that other engineers or non-experts build from.
Comfort operating as both a broad enabler, unblocking adoption across many teams, and a careful reviewer, gating what individual teams ship.

Nice To Haves

Experience setting up and administering AI coding tools or agent platforms, such as Claude Code, GitHub Copilot, or Cursor, across a team or company.
Familiarity with the Claude Agent SDK, Model Context Protocol (MCP), or comparable agent frameworks such as LangGraph, CrewAI, or AutoGen.
Experience building internal AI adoption programs: office hours, documentation, champion networks, or similar.
Background in code review, static analysis, or security review, enough to interpret gate findings without necessarily building the scanners.
Experience contributing to governance, approval, or escalation workflows for a technical platform.

Responsibilities

Partner with teams across Topgolf, technical and non-technical, to unblock AI adoption by configuring agent access, resolving friction, and showing teams how to get real value from available AI tools
Design and build archetypes and skills (e.g., SKILL.md files, intake questionnaires, spec templates, code scaffolds) that package engineering standards and governance into reusable building blocks for the AI-SDLC pipeline
Connect agents to internal systems, data sources, and tools through governed connectors and MCP-style integrations
Monitor archetypes and agents for model drift, prompt bloat, and other degradation as underlying models and usage evolve, and keep code scaffolds and prompts current with secure coding practices and platform engineering standards
Review AI agent-produced code, specs, and gate results for correctness, security, scope adherence, and good development practice before production
Test archetypes and agents against adversarial prompting (prompt injection, jailbreak attempts) and implement guardrail hooks to enforce scope, safety, and policy compliance
Build documentation, examples, and light training (office hours, walkthroughs, guides) to raise teams' baseline capability with AI
Retire, merge, or extend archetypes based on usage and escalation patterns, and triage escalations to security, data owners, or app stewards, partnering with platform engineering so new archetypes and integrations fit the pipeline's runtime and release mechanics
Triage escalations and route findings to security, data owners, or app stewards, following the pipeline's escalation rules.
Partner with the platform engineering team so new archetypes and integrations fit the pipeline's constrained runtime, connector catalog, and release mechanics.