Applied AI Specialist

Applied AI Specialist Overview

The Applied AI Specialist is a non‑traditional Business Analyst role within the AI Systems workstream, reporting to a Software Engineering Manager. Rather than traditional requirements gathering and process documentation, this role focuses on the critical intersection of AI capabilities and CNN’s content, editorial standards, and product experiences. Hands‑on with AI‑powered features—designing and refining prompts, building evaluation frameworks, structuring human feedback workflows, and working directly with engineering and editorial partners to ensure AI outputs meet CNN’s standards for accuracy and trustworthiness.

• Prompt Engineering – Design, build, iterate on, and maintain prompts for production AI features including article summaries, content classification, brand safety classification, and new features as they launch.
• Evaluation & Quality – Design evaluation criteria and workflows for AI features, build evaluation datasets, run quality assessments, and track accuracy over time.
• Human‑in‑the‑Loop Workflows – Design and execute workflows for human feedback on AI outputs, determine when human intervention is necessary, and capture feedback to improve models.
• Cross‑Functional Collaboration – Partner closely with engineers on technical implementation and editorial stakeholders on assigned projects, translating AI limitations into feature decisions and guidelines.

• Own the prompt engineering lifecycle for assigned AI features.
• Build and maintain evaluation frameworks that measure AI output quality against CNN’s editorial and accuracy standards.
• Design and run human review workflows, ensuring feedback is structured and actionable.
• Partner closely with engineers handling code, architecture, caching, optimization, and deployment.
• Work directly with editorial partners on assigned projects as the primary point of contact for AI output quality.
• Communicate nuances of working with LLMs—including stochastic nature, cost considerations, and evaluation importance—to teams.
• Contribute to documentation of prompting patterns, evaluation approaches, and quality standards.
• Stay current with developments in prompt engineering, LLM capabilities, and AI evaluation practices.

• Demonstrate meticulous attention to detail and responsibility for accuracy and quality of AI‑generated content.
• Bring strong domain knowledge of content, editorial processes, or classification systems.
• Embrace experimentation and iteration, systematically testing and refining.
• Communicate complex AI concepts in simple, practical terms to partners.
• Take ownership of quality, proactively identify issues and propose improvements.
• Collaborate effectively across functions, ensuring tight partnership between content experts, engineers, and editorial teams.
• Approach ambiguity with curiosity rather than hesitation; help define best practices.

• 2–4 years of experience in content operations, content classification, editorial workflows, taxonomy management, or a related field.
• Experience with prompt engineering for large language models in a professional or academic setting.
• Experience designing evaluation criteria or quality assessment workflows for content or AI outputs.
• Strong understanding of how LLMs work—including capabilities, limitations, stochastic behavior, and cost implications.
• Excellent written and verbal communication skills; ability to explain technical AI concepts to non‑technical audiences.
• Detail‑oriented with strong analytical skills and comfort working with evaluation data and quality metrics.
• Collaborative mindset and comfort working closely with software engineers and editorial stakeholders.
• Comfort navigating ambiguity in a fast‑evolving space; applied AI best practices still being established.

• Degree or certification in AI, machine learning, data science, or a related field.
• Experience with content classification, taxonomy, or content management systems.
• Experience in a news, media, or content‑heavy environment where accuracy and trust are paramount.
• Familiarity with AI evaluation frameworks, annotation tools, or…