You have a clear vision of where your career can go. And we have the leadership to help you get there. At CNA, we strive to create a culture in which people know they matter and are part of something important, ensuring the abilities of all employees are used to their fullest potential. 

JOB DESCRIPTION:

Essential Duties & Responsibilities

Performs a combination of duties in accordance with departmental guidelines:

• Build, apply, and promote adoption of platform-wide standards, reusable design patterns, and golden-path templates that enable product and feature teams to build, deploy, and operate AI solutions safely and consistently.
• Drive end-to-end delivery of new platform capabilities, from technical discovery and design through prototyping, hardening, and full production rollout, with hands-on involvement at critical technical milestones to ensure quality and coherence.
• Build and operationalize the core platform service catalog, including LLM gateway and routing layers, prompt lifecycle management, agentic orchestration frameworks, Retrieval-Augmented Generation (RAG) pipelines, vector stores, model registries, and rigorous automated evaluation infrastructure.
• Build and maintain robust CI/CD and AIOps pipelines for AI systems, incorporating automated evaluation gates, model and data versioning controls, staged deployment promotion, and continuous cost and performance optimization guardrails.
• Implement enterprise-grade multi-agent and single-agent workflow patterns for high-value business use cases, following clear standards for orchestration design, state and memory management, tool and API integration, and safe autonomy controls, including human-in-the-loop approvals, permission scoping, and comprehensive audit trails.
• Design and implement knowledge grounding systems, including hybrid retrieval strategies, semantic reranking, ontology-driven entity modeling, and knowledge graph integration, to measurably improve AI output accuracy, explainability, traceability, and readiness for regulatory audit.
• Embed responsible AI and compliance-by-design principles across the platform, covering data privacy protections, enterprise secrets management, granular access controls, output leakage prevention, and model risk governance practices aligned to enterprise and regulatory standards.
• Participate in code and design reviews, and contribute to testing, documentation, and operational readiness.

May perform additional duties as assigned.

Reporting Relationship

Typically Director or above

Skills, Knowledge & Abilities

• Deep AI platform and AIOps engineering expertise, with hands-on experience building, deploying, and operating shared AI platform capabilities such as model serving layers, LLM gateway and proxy services, prompt registries, vector databases, and automated evaluation harnesses at enterprise scale.
• Proven agentic system design capability, with hands-on experience building multi-agent and single-agent workflow systems using orchestration frameworks such as LangGraph and Google ADK, including tool and function calling patterns, state and memory persistence strategies, and robust safe autonomy controls.
• Applied GenAI depth spanning LLM solution architecture patterns, model selection and routing strategies, advanced prompt engineering techniques, fine-tuning and RLHF tradeoffs, and production-grade RAG and hybrid retrieval system design and optimization.
• Strong cloud-native and distributed systems skills, with deep GCP expertise across Vertex AI, Cloud Run, GKE, Pub/Sub, and BigQuery, and a solid command of API and service-based design, event-driven architecture, and high-availability and fault-tolerant system patterns.
• Knowledge grounding and semantic layer proficiency, including experience building canonical ontology and entity models, designing vector search and hybrid retrieval pipelines, integrating knowledge graphs, implementing reranking strategies, and establishing citation and traceability mechanisms that support explainability and compliance.
• Solid AIOps and platform reliability engineering experience, including CI/CD pipeline design for AI systems, automated evaluation and quality gates, model and dataset versioning, production monitoring and observability, reliability engineering practices, and systematic cost-performance optimization.
• Practical responsible AI and security expertise, with experience implementing enterprise AI governance frameworks, model risk management practices, PII and data privacy controls, audit and event logging, and compliance-by-design patterns suited to regulated industries.
• Strong SDLC and hands-on engineering fundamentals, including Python proficiency, architectural and code review practices, comprehensive testing strategies for AI systems, technical debt management, refactoring discipline, and operational readiness standards.
• Familiarity with Scaled Agile (SAFe), including contributing to Enabler Epics and PI planning.
• Strong communication skills, with the ability to collaborate with engineers, product partners, and business stakeholders, negotiate technology tradeoffs, mentor junior engineers, and explain technical concepts clearly to non-technical audiences.

Education & Experience

• Bachelor’s degree in Computer Science, Software Engineering, Information Technology, or equivalent required; Master’s degree in AI, Machine Learning, Data Science, or a related discipline strongly preferred.
• 8+ years in software engineering and technical delivery, including work on large-scale, distributed enterprise systems across the full SDLC, from inception through production operations.
• 5+ years hands-on designing, delivering, and operating AI/ML or GenAI platform capabilities in production, with measurable outcomes in quality, reliability, and developer adoption.
• Strong Python proficiency and deep practical GCP experience (Vertex AI, GCP Agent Builder, and Gemini), with the ability to do hands-on technical work as part of the engineering team.
• Prior experience in regulated industries (insurance, financial services, or healthcare) strongly preferred, given stringent governance, auditability, and model risk management requirements.
• Consulting or enterprise delivery background is a plus, bringing structured problem-solving and stakeholder management.

#LI-KJ1 #LI-HYBRID

In certain jurisdictions, CNA is legally required to include a reasonable estimate of the compensation for this role. In District of Columbia, California, Colorado, Connecticut, Illinois, Maryland, Massachusetts, New York and Washington, the national base pay range for this job level is $72,000 to $141,000 annually. Salary determinations are based on various factors, including but not limited to, relevant work experience, skills, certifications and location. CNA offers a comprehensive and competitive benefits package to help our employees – and their family members – achieve their physical, financial, emotional and social wellbeing goals.  For a detailed look at CNA’s benefits, please visit cnabenefits.com.

CNA utilizes AI-enabled technology during the recruiting process. For more information, please visit our careers page.

CNA is committed to providing reasonable accommodations to qualified individuals with disabilities in the recruitment process. To request an accommodation, please contact leaveadministration@cna.com