Principal Full Stack Engineer, AI Platform & Agents

About this role

Our team is building a central GenAI Platform to empower hundreds of product teams across the organization with scalable capabilities for rapid development, validation, and deployment of AI agents. We also drive the development of the most impactful AI agents, ensuring faster delivery and greater impact across multiple domains. With over 20 agents already launched and many more in progress, our work accelerates innovation and improves outcomes in critical industries.

You'll join a 100-engineer team within a larger organization that combines the stability of an established company with the agility of a startup. In this high-autonomy, high-impact role, you'll take problems from concept to production, mentor less experienced engineers, and lead by example. You'll design and ship full-stack systems, shape platform capabilities to empower hundreds of product teams, and directly contribute to the development of the most impactful AI agents.

Flagship Agent: UpToDate Expert AI

In Health, we’re launching UpToDate Expert AI—a medical research and clinical reasoning agent that transforms the world’s most widely used point‑of‑care knowledge resource into a real‑time medical assistant. Millions of physicians will rely on it to accelerate differential diagnosis, refine treatment decisions, and reduce cognitive load—while maintaining rigorous safety, privacy, and guideline fidelity. Improvements you ship (latency, reliability, hallucination reduction) will translate directly into faster, higher-quality patient care at global scale.

What you’ll do

• Design and implement full‑stack applications, AI agents, and platform components that enable rapid GenAI agent development, validation, and deployment.
• Build developer tooling, CI/CD, and observability for safe, fast iteration (evals, canaries, rollout/rollback, cost and quality telemetry).
• Apply secure SDLC and privacy‑by‑design practices (threat modeling, least privilege).
• Collaborate with product, UX, and domain experts to deliver customer‑focused solutions with measurable outcomes.
• Apply current LLM patterns (RAG, retrieval, routing, tool-use, evals) to deliver measurable customer value—faster, more reliable AI systems; reduced time-to-decision; improved trust/safety metrics; and lower cost per query.
• Lead by example and be heavily hands-on: drive architecture, mentor engineers, and take ownership of larger projects.

Minimum qualifications

• 8+ years of professional software engineering experience.
• Strong full‑stack development skills and cloud experience (AWS/Azure/GCP).
• Expert in at least one, and proficient across the others:
• AI Agent development and evaluation
• Backend development
• Frontend development
• Cloud services (AWS/Azure/GCP)
• CI/CD and Infrastructure as Code
• Site Reliability Engineering (SRE)
• Quality engineering / testing strategy
• Secure SDLC and privacy by design
• Proven track record delivering secure, reliable, cloud‑native systems to production.
• Excellent problem‑solving, ownership, and cross‑functional communication.

Nice to have

• Proven ability to deliver software products independently or as part of a small, fast-paced team.
• Experience of taking AI agents from concept to production, including safety evaluations, iterative testing (e.g., A/B testing), and continuous improvement.
• Experience with LangChain/LangGraph and MCP; vector/RAG systems; OpenSearch.
• Worked on traditional ML tasks like training, deployment, and monitoring.
• Understand how LLMs work, their failure modes, and techniques like fine-tuning and model adaptation.
• Familiarity with regulatory frameworks such as SOC2, HIPAA, etc.

Applicants may be required to appear onsite at a Wolters Kluwer office as part of the recruitment process.