Sr AI Solutions Specialist - Architecture Foundry

Are you a highly versatile developer who is passionate about translating cutting‑edge Generative AI research into production‑ready software? Do you want to build the smart interfaces, agentic workflows, and automated microservices that will power the future of financial markets? CME Group is seeking a Sr AI Solutions Specialist to join our revolutionary Architecture Foundry within the Central Hub. Sitting inside our innovative, cross‑functional "Architecture-as-a-Product" pod, you will partner directly with Enterprise Architects and Cloud Platform Engineers to turn visionary architectural concepts into living, breathing AI‑powered solutions.

In this role, you will be the premier Force Multiplier for our applied architecture stories and epics. Rather than building isolated models, you will act as a versatile, multi‑disciplinary AI specialist.

• Build Reusable AI Assets:
  Design, build, and maintain enterprise‑grade software templates, reusable SDKs, and modular microservices that wrap GenAI capabilities (e.g., prompt management, retrieval‑augmented generation [RAG], embeddings) into standard developer tools.
• Architect AI Agents:
  Design and deploy robust multi‑agent systems and agentic architectures capable of planning, reasoning, memory retention, tool usage, and execution across complex enterprise APIs.
• Translate Architecture into Code:
  Partner with Enterprise Architects to implement their strategic design patterns, turning abstract standards into functional codebases that prove the viability of next‑generation AI platforms.
• Prototype to Production (MVPs):
  Rapidly develop functional prototypes and proof‑of‑concepts (POCs) for high‑impact AI use cases, ensuring code is clean, modular, and optimized for production hand‑off.

• Democratize AI Best Practices:
  Package your code into clear, well‑documented starter kits and boiler plates, making it incredibly simple for delivery teams to integrate advanced AI without reinventing the wheel.
• Co‑Create Paved Paths:
  Work with the Pattern Council to certify and publish your templates as standard developer building blocks.
• Collaborative Support:
  Embed briefly with engineering pods to help them adopt your templates, troubleshoot complex API/LLM integration issues, and scale their implementations.

3–5+ years of progressive, hands‑on software engineering experience, with a proven track record of writing production‑grade, highly reusable, and modular code libraries.

Experience working within large, complex corporate environments or financial services institutions, demonstrating familiarity with enterprise security standards, data privacy controls, and API‑driven architectures.

Bachelor’s or Master’s degree in Computer Science, Software Engineering, or a related technical discipline.

Deep proficiency in Python (the industry standard for AI enablement) alongside experience in enterprise languages (e.g., Java, C++, or Node.js).

Hands‑on experience developing applications using state‑of‑the‑art Large Language Models (LLMs) from Google (Gemini/Vertex AI), OpenAI, or open‑source ecosystems.

Proven experience building agentic workflows and multi‑agent orchestration systems using frameworks such as Lang Graph, Auto Gen, CrewAI, or Google Vertex AI Agent Builder.

Strong understanding of semantic search, vector databases (e.g., Pinecone, pgvector), chunking strategies, prompt engineering patterns, and RAG architectures.

Advanced skills in building and consuming RESTful/gRPC…