Senior AI Engineer, Full-Stack — Agent Factory

Job description

Your work days are brighter here. We’re obsessed with making hard work pay off, for our people, our customers, and the world around us. As a Fortune 500 company and a leading AI platform for managing people, money, and agents, we’re shaping the future of work so teams can reach their potential and focus on what matters most. The minute you join, you’ll feel it. Not just in the products we build, but in how we show up for each other. Our culture is rooted in integrity, empathy, and shared enthusiasm. We’re in this together, tackling big challenges with bold ideas and genuine care. We look for curious minds and courageous collaborators who bring sun-drenched optimism and drive. Whether you're building smarter solutions, supporting customers, or creating a space where everyone belongs, you’ll do meaningful work with Workmates who’ve got your back. In return, we’ll give you the trust to take risks, the tools to grow, the skills to develop and the support of a company invested in you for the long haul. So, if you want to inspire a brighter work day for everyone, including yourself, you’ve found a match in Workday, and we hope to be a match for you too. About the Team Agent Factory is where Workday's next chapter gets built. Within our AI organization, small, senior, cross-functional pods bring together product leaders, machine learning engineers, UX designers, and full-stack builders to create intelligent agents used by millions of people every day. This is production-grade AI embedded deeply into Workday's platform — not research experimentation or maintenance work. We ship to paying enterprise customers today, and we're kicking off a new AI agent initiative that will define how our products reason and act on behalf of users. High trust, high expectations, and real impact. Engineering, but brighter. About the Role You'll own the end-to-end design, implementation, and product integration of our intelligent agents — and build the full-stack product surface those agents live in. Our ML Engineers build and optimize the foundational algorithms; your mission is intelligence orchestration and product delivery, connecting the brain to the product. Expect to be hands-on across React frontends, backend microservices, APIs, data models, asynchronous workflows, agent orchestration layers, and delivery infrastructure. Because these agents work with sensitive HR and financial data at global scale, you'll help implement the guardrails that keep them private, predictable, and explainable. This is the most senior engineering role on the team. You'll set the technical direction for our agent architecture, mentor the engineers around you, and be the person who presents the work when the stakes and visibility are highest. Design and implement agentic workflows — orchestration and routing layers, tool calling, retrieval pipelines, memory, and multi-step reasoning — and integrate foundation models into customer-facing HR and Finance workflows. Build and operate end-to-end features across React frontends, backend microservices, APIs, data models, and CI/CD. You build it, you run it. Own the constraints that make agents viable in production: latency, cost per interaction, context-window efficiency, determinism, and graceful failure. Build the evaluation loop — offline and online evals, benchmarking agent behavior against product requirements, and production observability of agent traces. Implement Responsible AI in practice: guardrails, permission and data-boundary enforcement, PII handling, auditability, and explainability. Lead high-visibility projects end to end and present them with confidence in design reviews, demos, and executive updates. Make the call when the team needs one — gather input quickly, commit to a direction, document the trade-offs, and adjust as evidence arrives. Mentor engineers, raise the technical bar, and partner closely with Product, UX, Machine Learning, and platform teams. About You Basic Qualifications 10+ years of professional software development experience, including significant full-stack ownership from modern frontend through backend services. 5+ years with backend web frameworks; Python frameworks such as FastAPI, Flask, or Django preferred. 2+ years integrating large models (LLMs, foundation models) and modern AI APIs into production, user-facing products. 1+ years designing and scaling AI orchestration architectures — multi-agent or tool-calling frameworks, routing layers, or advanced RAG pipelines. 4+ years using cloud platforms (e.g., AWS, GCP) to deploy responsive, scalable systems. Other Qualifications Track record of shipping AI and agentic features that real customers use in production, and owning them after launch — prototypes alone aren't the bar. Product-first mindset: you apply large models to solve practical user problems, not to showcase the technology. Practical command of LLM constraints (token and cost management, context-window efficiency, caching, streaming, fallbacks) and of evaluation — rapid prototyping, benchmarking outputs, and automated metrics for retrieval quality and agentic behavior. Strong understanding of the governance, guardrails, and security layers required when deploying autonomous agents over sensitive enterprise data. Proven ability to architect the application layer around AI models: reusable patterns for predictability, error handling, and seamless UX integration. Strong experience with React or a comparable framework, TypeScript, state management, and modern build tooling, plus a commitment to accessibility (WCAG 2.1/2.2). Deep knowledge of backend service architecture, microservice patterns, and REST API design, with proficiency in Python and ideally Kotlin or Java. 5+ years with relational databases (PostgreSQL preferred) and non-relational stores, including query analysis and indexing optimization. Strong grasp of distributed-system trade-offs, with the ability to independently diagnose and optimize performance at scale. Hands-on with I