Principal AI Engineer

Continental Casualty Company•Chicago, IL

About The Position

The Principal AI Engineer is an individual contributor providing the highest level of technical leadership in the design, development, and scaling of CNA’s AI-native agentic engineering platform. The role works across AI systems engineering, developer experience, and software delivery to build foundational capabilities that help the engineering organization build, ship, and run high-quality, secure AI-native systems. The platform focus includes agentic workflows, AI-augmented CI/CD pipelines, reusable skills and agent frameworks, and quality and security guardrails. The role leads the design of the platform’s end-to-end system, integrates AI tools into the software delivery lifecycle, and establishes agentic infrastructure and development practices. It provides technical consultation to engineering leaders and portfolio teams, advises on appropriate AI autonomy and human review for different risk profiles, and leads the technical strategy and implementation of an engineering metrics platform. It also mentors engineers, evaluates tools and infrastructure, and partners with Architecture, Security, Cloud Engineering, and Data teams to support enterprise integration, compliance, and scale.

Requirements

Bachelor’s degree in Computer Science, AI/ML, or a related discipline, or equivalent work experience.
At least 9 years of diverse software engineering work experience, including at least 6 years in application development.
At least 2 years of recent experience building or operating AI-augmented development tools, agentic systems, or developer platforms.
Hands-on experience using LLM-based engineering tools such as Claude Code, Cursor, GitHub Copilot, or equivalent in production engineering workflows.
Expert knowledge of AI-native software engineering practices, including agentic coding workflows, prompt and context engineering, multi-agent orchestration, MCP protocol, and skill or agent authoring patterns.
Deep understanding of the software delivery lifecycle and how AI applies to requirements, design, code generation, testing, code review, and continuous deployment.
Proficiency building and operating CI/CD platforms such as GitHub Actions or equivalent, infrastructure as code such as Terraform, container orchestration such as GKE/Kubernetes, and cloud platforms such as GCP.
Strong knowledge of application security engineering, including supply-chain security, artifact management and curation, static and dynamic analysis, secret management, and AI-generated-code risks such as dependency hallucination, model drift, and prompt injection.
Demonstrated ability to design developer platforms and tooling for hundreds of engineers with varying skill levels while balancing power-user capabilities with guardrails.
Ability to evaluate and integrate emerging AI technologies rapidly and distinguish production-ready capabilities from hype.
Excellent communication skills and ability to explain complex AI engineering concepts to technical and non-technical audiences.
Ability to influence engineering culture and adoption across a large, diverse organization, including internal teams and managed service providers.
Strong analytical and problem-solving skills, with an outcomes-oriented focus on delivery speed, code quality, and engineering productivity.

Nice To Haves

Master’s degree in Computer Science, AI/ML, or a related discipline.
Experience designing and scaling inner-source or platform engineering programs across large engineering organizations.
Applicable certifications in cloud platforms such as GCP or AWS, AI/ML, or security.

Responsibilities

Design the end-to-end AI-native engineering platform, including agentic coding workflows, skills and agent marketplaces, AI-augmented CI/CD pipelines, automated quality gates, and rapid environment provisioning.
Lead integration of AI tools such as Claude Code, Cursor, and GitHub Copilot into the software delivery lifecycle as part of 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 practices.
Advise engineering leadership, portfolio teams, and architecture on AI-native development practices, AI-generated code quality, and integration of agentic tools into existing workflows.
Guide decisions about speed and quality trade-offs, human-in-the-loop requirements, and appropriate AI autonomy for different risk profiles.
Lead the technical strategy and implementation of the engineering metrics platform, and consult with senior technology leadership on data-driven decision-making.
Mentor engineers across the organization in agentic coding, context engineering, prompt-to-code workflows, and AI-assisted testing to build self-sustaining capability.
Research, evaluate, and recommend AI engineering tools, frameworks, and infrastructure aligned with CNA’s strategic direction.
Lead build-versus-buy analysis for capabilities such as CI/CD tooling, sandbox provisioning, and LLM evaluation infrastructure.
Partner with Architecture, Security, Cloud Engineering, and Data teams to integrate the platform with enterprise infrastructure, meet regulatory and compliance requirements, and scale across portfolios and engineering teams.
Perform additional duties as assigned.