Senior Software Engineer - AI Enablement

Workiva•Ames, IA

5d•Hybrid

About The Position

As a Senior Software Engineer, you will be the technical engine of the AI Enablement team. Your mission is to bridge the gap between "AI-adjacent" and "AI-native" by building the tools and integrations that make AI indispensable to the PDLC. While you will contribute across our entire stack, you will be expected to own a specific domain—such as our Model Context Protocol (MCP) ecosystem, wk-ai-prototyping repo or our future automated testing agents—becoming the go-to expert for that area while maintaining the flexibility to support the broader team.

Requirements

4+ years of related software development experience.
Strong proficiency in back-end services, proxy servers, and API integrations.
Experience with Python, Go, or TypeScript is preferred.
Extensive experience using AI-augmented IDEs (e.g., Cursor, Claude Code) to maintain high throughput and quality.
Ability to translate complex technical implementations into clear, actionable documentation for the broader engineering org.

Responsibilities

Take deep ownership of a specific technical domain (e.g., our MCP server infrastructure or wk-ai-prototyping repo). Be the primary maintainer and visionary for this component.
Architect and maintain internal MCP servers (integrating Jira, Splunk, Datadog, etc.) and deploy cloud-hosted autonomous agents within FedRAMP boundaries.
Independently deliver software solutions through a set of milestones, ensuring code is sustainable, reusable, and optimized for an AI-augmented environment.
Conduct deep technical spikes on emerging AI tools (e.g., Qodo, Cursor, Claude Code) to ensure compatibility with Workiva’s architecture and security standards.
Actively surface and document "Golden Paths"—creating playbooks that standardize how engineers utilize AI to reduce KTLO (Bugfixes, CVEs, Migrations).
Serve as a tactical consultant for product teams, helping them integrate AI agents into their specific workflows and troubleshooting technical blockers.
Implement and monitor metrics (using tools like Mstone) to measure the impact of AI on team velocity and code quality.
Level up team members by providing guidance on AI-augmented development techniques and conducting "Review-First" code reviews.
Showcase successful use cases and strategic wins in engineering syncs to encourage organic AI adoption.