Applied AI Engineer

We are seeking an Applied AI Engineer to serve as a high-impact bridge between human domain expertise and production AI execution.

In this role, you will own the end-to-end authoring, prompt architecture, and API integration of AI skills that power Workday's core agentic capabilities.

This is a pivotal, high-visibility engineering position with cross-organizational impact. You will work directly with top Subject Matter Experts across business units to translate complex enterprise logic, tribal configuration knowledge, and standard operating procedures into deterministic, schema-compliant AI tools using state-of-the-art AI-assisted development environments.

Responsibilities:

• Enterprise Skill Authoring & Domain Codification: Partner directly with domain experts and senior consultants across business units to translate complex business logic, prose, and raw scripts into optimal, structured AI skill definitions.
• AI-Assisted Editor Mastery: Operate at the cutting edge of AI-driven software development (using Cursor, Claude Code, and custom tooling) to rapidly generate, refactor, and refine prompt logic, tool descriptions, and Model Context Protocol (MCP) tool calls.
• API & Capability Orchestration: Connect skills to backend systems by wiring up enterprise REST APIs, MCP servers, and complex data structures for seamless agent execution.
• Logic Optimization & Deduplication: Abstract messy business procedures into clean, modular logic,separating prose from executable code while optimizing prompt structures for minimal token consumption and maximum execution reliability.
• Edge-Case Stress Testing: Design and implement automated test suites to stress-test skill edge cases, API parameter bounds, fallback logic, and error-handling routines before deployment.
• Enablement & Code Review: Scale authoring standards across Workday by establishing best practices, training domain experts on self-serve authoring workflows, and reviewing submitted skill pull requests for schema compliance and API integrity.
• Enforce Evaluation-Driven Development (EDD): Partner with Domain Experts to curate benchmark eval datasets, implementing LLM-as-a-Judge scoring, trajectory trace analysis, and CI/CD quality gates to validate skill accuracy and prevent regressions prior to production promotion.
• Production Telemetry & Drift Analysis: Establish feedback loops using production agent trace logs to identify trajectory failures, update eval benchmark suites, and continuously improve skill deterministic behavior.

Requirements:

• 4+ years of professional software engineering experience in Python or TypeScript with a focus on API integrations, backend services, or scripting.
• 1+ years of hands-on experience leveraging AI-assisted development tools (e.g., Cursor, GitHub Copilot, Claude Code) to author, refactor, and debug production code.
• Strong experience working with REST APIs, JSON/YAML schemas, and structured data transformations.
• Bachelor's degree in Computer Science, Engineering, or a related field, or equivalent practical experience.

Nice to Have:

• Strong technical communication and interpersonal skills to collaborate effectively with non-technical domain experts and translate requirements into clean technical specs.
• Generative AI & Tool Calling: Solid grasp of prompt engineering, function calling, structured outputs, and agentic specifications (e.g., Model Context Protocol / MCP).
• Code Refactoring & Systems Rigor: Ability to dissect complex domain scripts or unstructured documentation and refactor them into modular, testable, production-ready code.
• Testing & Quality Mindset: Experience writing unit/integration test cases, mocking API dependencies, and debugging schema mismatches.
• Strategic Agility: Ability to ramp up quickly on new business domains (e.g., moving from HR payroll logic to complex tax or financial workflows) and deliver high-impact capabilities in rapid iteration cycles.
• Experience building or operating LLM evaluation frameworks (e.g., Ragas, DeepEval, Braintrust, LangSmith, or custom assertion suites) to benchmark tool-calling accuracy, prompt drift, and agent success rates.

Salary: €72,000 EUR - €108,000 EUR

Work Arrangement: With Flex Work, we're combining the best of both worlds: in-person time and remote. Our approach enables our teams to deepen connections, maintain a strong community, and do their best work.