AI Prompt Engineer, Trust Review Operations

LinkedIn is the world's largest professional network, built to create economic opportunity for every member of the global workforce. Our products help people make powerful connections, discover exciting opportunities, build necessary skills, and gain valuable insights every day. We're also committed to providing transformational opportunities for our own employees by investing in their growth. We aspire to create a culture that's built on trust, care, inclusion, and fun – where everyone can succeed.

Join us to transform the way the world works.

This role is based in Dublin, Ireland

At LinkedIn, our approach to flexible work is centered on trust and optimized for culture, connection, clarity, and the evolving needs of our business. The work location of this role is hybrid, meaning it will be performed both from home and from a LinkedIn office on select days, as determined by the business needs of the team.

LinkedIn’s Trust Review Operations team protects our global community by ensuring AI‑driven moderation systems are safe, accurate, and reliable. As an AI Prompt Engineer (IC3), you will design, test, refine and evaluate prompts and workflows that assist in content moderation, improve detection quality, and support reviewer decision‑making.

This role is ideal for someone who enjoys hands‑on experimentation, analyzing model behaviour, and partnering with Policy, Engineering, and Data Science to improve safety outcomes.

What You’ll Do

Responsibilities

Design and refine prompts for classification, risk detection, case summarization, and reviewer support.; Run prompt experiments to diagnose issues such as hallucinations, misclassifications, bias, or inconsistent behaviour.; Help maintain evaluation frameworks for accuracy, safety, and reliability.; Support AI‑assisted workflows in resolving medium and high‑risk cases.; Identify model errors, document patterns, and recommend improvements to reduce operational risk.; Contribute to operational guardrails and escalation criteria for AI behaviour.; Flag AI output issues (e.g., inconsistent decisions, low‑confidence outcomes, override trends).; Participate in incident reviews and help document root‑cause insights.; Ensure AI outputs align with platform policies, MDSS, and relevant regulations (e.g., DSA).; Work with policy experts to translate reviewer feedback into clearer prompts and rules.; Collect feedback from reviewers, policy partners, and operational teams to refine prompts.; Translate qualitative insights into structured requirements for Engineering and Data Science.; Analyze prompt and evaluate model performance using SQL or dashboards.; Track trends such as classifier drift, emerging abuse patterns, or changes in harmful content.; Contribute data‑backed insights that inform roadmap and workflow updates.

Requirements

Bachelor’s degree in Data Science, AI/ML, Engineering, Policy, or related field (or equivalent experience).; 4+ years of experience in Trust & Safety, content moderation, AI operations, quality, or policy.; 2+ years experience designing or testing prompts or working with LLMs / classification models.; 2+ years experience with evaluation metrics (precision, recall, FPR, FDR) and model quality testing.; 2+ years experience with AI coding assistants (Github CoPilot, Claude code or equivalent agentic CLI tools) used to build, test, iterate on and evaluate prompts.; Prompt Engineering; Model or Agent Evaluation; Analytical Thinking; Data Interpretation; Problem Solving; Technical Curiosity; Written & Verbal Communication; Collaboration & Stakeholder Support; Quality & Detail Orientation; Adaptability in fast‑changing environments

Nice to have

Understanding of Trust & Safety policies, global regulations (e.g., DSA), and safety standards.; Experience collaborating with Product, Engineering, Policy, or Data Science teams.; Exposure to human‑in‑the‑loop workflows, generative AI systems, or safety‑centric model evaluation.; Ability to analyze model outputs and identify patterns, gaps, and risks.; Strong written communication skills for writing clear, reproducible prompt instructions.; Proficiency using data tools (e.g., SQL and python) to evaluate model and prompt performance.