Principal AI Engineer

Join CNA to build an AI-native engineering platform that helps teams deliver with speed and governance in the same system. This role is an individual contributor with principal-level technical leadership, helping design and scale capabilities like agentic workflows, AI-augmented CI/CD pipelines, reusable skills and frameworks, and automated quality and security guardrails. Work is based in Chicago, IL in a hybrid setup.

In this position, you will influence how engineers across the organization adopt AI-native development practices, while partnering with Architecture, Security, Cloud Engineering, and Data to ensure the platform integrates with enterprise infrastructure and supports compliance needs (including AI model tracking and Sox controls).

What you’ll do

• Serve as a principal engineer on CNA’s AI-native engineering platform, designing end-to-end systems across agentic coding workflows, skills and agent marketplaces, AI-augmented CI/CD pipelines, automated quality gates, and rapid environment provisioning.
• Lead integration of AI tooling (including Claude Code, Cursor, and GitHub Copilot) into the software delivery lifecycle so capabilities work together as a coherent, governed platform.
• Design and build the agentic infrastructure layer, including multi-agent orchestration patterns, sub-agent frameworks, skill authoring standards, and context engineering best practices.
• Advise engineering leadership and portfolio teams on adopting AI-native development practices, evaluating AI-generated code quality, and integrating agentic tooling into existing workflows.
• Recommend where to apply AI autonomy by advising trade-offs between speed and quality, human-in-the-loop requirements, and autonomy levels aligned to risk profiles (for example, Sox-classified systems versus rapid prototyping).
• Lead technical strategy for centralized skills and agent marketplace, defining contribution standards, review processes, and governance models for inner-source contribution at scale while maintaining enterprise quality and security requirements.
• Define what qualifies as a skill, an agent, and an MCP configuration at the enterprise level.
• Act as a senior technical resource mentoring engineers across the organization in AI-native engineering practices, including agentic coding patterns, context engineering, prompt-to-code workflows, and AI-assisted testing.
• Research, evaluate, and recommend AI engineering tools, frameworks, and infrastructure such as eval platforms, agent orchestration systems, and environment provisioning automation.
• Lead build-versus-buy decisions for platform capabilities including CI/CD tooling, sandbox provisioning, and LLM evaluation infrastructure.
• Partner with teams across Architecture, Security, Cloud Engineering, and Data to integrate the platform with enterprise infrastructure (including GCP/GKE, GitHub, and JFrog Artifactory) and scale to support hundreds of engineers and AI pod teams across portfolios.

What you bring

• Expert knowledge of AI-native software engineering practices, including agentic coding workflows (Claude Code, Cursor, GitHub Copilot), prompt and context engineering, multi-agent orchestration, MCP protocol, and skill/agent authoring patterns.
• Deep understanding of the modern software delivery lifecycle and how AI transforms each phase, from AI-assisted requirements and design through agentic code generation, automated testing, AI-augmented code review, and continuous deployment.
• Expert-level experience building and operating CI/CD platforms (GitHub Actions or equivalent), infrastructure-as-code (Terraform), container orchestration (GKE/Kubernetes), and GCP, with the ability to enforce quality and security gates without slowing delivery.
• Strong application security engineering knowledge, including supply chain security, artifact management, static/dynamic analysis, secret management, and awareness of AI-specific risks such as dependency hallucination, model drift, and prompt injection.
• Proven ability to design developer platforms and tooling that serve hundreds of engineers at varying experience levels, balancing capability with guardrails for quality and safe usage.
• Track record evaluating and integrating emerging AI technologies quickly, with judgment to separate production-ready capability from hype.
• Excellent communication skills, including translating AI engineering concepts for technical and non-technical audiences.
• Ability to influence engineering culture and drive adoption across internal teams and managed service providers.
• Strong analytical and problem-solving skills with an outcomes focus on measurable improvements in delivery speed, code quality, and engineering productivity.

Tools you’ll work with

• Claude Code, Cursor, GitHub Copilot
• GitHub Actions, Terraform, GKE/Kubernetes, GCP
• GitHub, JFrog Artifactory
• MCP protocol, LLM evaluation infrastructure, eval platforms
• Agent orchestration systems, environment provisioning automation
• Multi-agent orchestration, sub-agent frameworks, inner-source
• AI model tracking, Sox controls

Compensation and benefits

Salary range: USD 97,000 - 189,000 per year.

CNA offers a comprehensive and competitive benefits package. Learn more at cnabenefits.com.

Experience and education

• Minimum of 9 years of solid, diverse software engineering experience, including at least 6 years in application development.
• Significant recent experience (2+ years) building or operating AI-augmented development tools, agentic systems, or developer platforms.
• Hands-on production experience with LLM-based engineering tools (Claude Code, Cursor, GitHub Copilot, or equivalent), not limited to experimental use.
• Experience designing and scaling inner-source or platform engineering programs across large engineering organizations is preferred.
• Applicable certifications in cloud platforms (GCP, AWS), AI/ML, or security are preferred.
• Bachelor’s degree with Master’s preferred in Computer Science, AI/ML, or a related discipline, or equivalent work experience.

Reporting relationship: Typically Director or above.