Platform Engineer I

CME Group•Chicago, IL

1d•$73,500 - $122,500

About The Position

The Data Platform team builds and maintains CME Group’s enterprise knowledge catalog, knowledge graph, unified data pipelines, and BigQuery and analytics ecosystem. The Platform Engineer I will build AI data agents that interact with these systems, automate complex data workflows, contribute to intelligent and reusable data pipeline tooling, and create scalable integrations connecting AI capabilities with core data platforms. The role includes designing AI agents and modular Agent Skills, implementing evaluations to assess agent reliability and factual consistency, integrating with data pipelines and analytics systems, and collaborating with data engineers to expand the enterprise knowledge catalog and graph. The position uses coding-agent tools to accelerate technical delivery and works across cloud, API, containerization, orchestration, and CI/CD environments. CME Group describes its total rewards package as including an annual target bonus opportunity and broad-based equity program. Benefits include health coverage, a retirement package with a 401(k) and active pension plan, education reimbursement, paid time off, and a mental health benefit. The stated pay range is $73,500–$122,500; the actual offer depends on factors including relevant experience, skills, education, and internal comparisons.

Requirements

Bachelor’s degree, preferably in Computer Science, Information Systems, or a related discipline.
At least 1 year of relevant hands-on engineering experience.
Strong proficiency in Python and Java.
Hands-on experience building AI agents using Google ADK and LangChain.
Direct experience developing Agent Skills and building Agent Evals.
Experience using coding-agent tools, including Claude, Anti Gravity, and GitHub Copilot, in the software development lifecycle.
Ability to work proactively in a team environment and meet delivery timelines.

Nice To Haves

Experience with knowledge graphs, enterprise data catalogs, semantic data models, and data pipelines.
Hands-on experience with Google Cloud Platform and deep knowledge of BigQuery.
Experience with GitOps practices and deploying applications to Kubernetes.
Experience working with Gemini, Anthropic, or GPT models.
Experience with AWS or Azure.
Proficiency in SQL, Go, Scala, and Ruby.
Experience with prompt engineering, context engineering, Retrieval-Augmented Generation architectures, and AI model evaluation.
Experience with cloud environments, Kubernetes, Docker, Google Artifact Registry, Docker Hub, Argo Workflows, Argo CD, Terraform, Kubernetes Config Connector, Git, Maven, Jenkins, and automated CI/CD pipelines.
Experience processing JSON, YAML, Avro, Parquet, and ORC.
Relevant cloud or DevSecOps professional certifications, such as AWS or GCP certifications.

Responsibilities

Design, build, and deploy AI data agents that query and navigate the enterprise knowledge graph, data catalogs, and analytics systems.
Develop modular Agent Skills for data retrieval, transformation, and analytical tasks.
Design and implement Agent Evals to test the reliability, accuracy, and factual consistency of agent outputs.
Build intelligent integrations and reusable tooling for unified data pipelines and BigQuery ecosystems.
Collaborate with data engineers to ingest, curate, and expand the enterprise knowledge catalog and knowledge graph.
Use coding-agent tools to accelerate technical delivery and code generation.
Build and consume REST and GraphQL APIs for enterprise data marketplace ecosystems.
Apply cloud security principles, API security protocols, secure coding standards, and cloud application security frameworks.
Manage containerized applications and automate workflows and infrastructure using the tools and platforms described in the posting.
Execute system testing to optimize data pipeline performance and API endpoint efficiency.
Deliver projects using Agile methodologies and DevSecOps continuous integration and delivery practices.
Solve technical problems independently and collaboratively, deliver on time, and communicate clearly with cross-functional teams.