Senior AI Prompt Engineer, Trust Review Operations

This role will be based in Dublin Ireland.

At LinkedIn our approach to flexible work is centered on trust and optimised 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 was built to help professionals achieve more in their careers andeverydaymillions of people use our products to make connections discover opportunities and gain insights. Our global reach means we get tomakea direct impact on the worlds workforce in ways no other company can. Were much more than a digital resume we transform lives through innovative products and technology. 

Searching for your dream job At LinkedIn we strive to help our employees find passion and purpose. Join us in changing the way the world works.

The Senior AI Prompt Engineer plays a critical role in how LinkedIn leverages AI to enhance safety trust and operational excellence across our platform. You will design evaluate and optimize prompts and AIdriven workflows to improve moderation quality operational efficiency and classifier performance.

You will lead complex prompt experimentation conduct investigations into model behavior partner crossfunctionally to drive system improvements and ensure alignment with policy safety standards and global regulatory frameworks.

This role is ideal for someone who operates at the intersection of AI systems content safety operational rigor and policy alignment and wants to influence the future of AIassisted Trust Review Operations at scale.

What Youll Do

• Lead initiatives with Product Engineering Data Science Policy and Research to advance AIenabled Trust & Safety workflows.

• Drive alignment on prompt engineering strategies classifier improvements and modeldriven risk mitigation.

• Communicate effectively across technical and nontechnical audiences to guide adoption of AI tooling.

• Mentor peers involved in AI experimentation orchestration or operational testing.

• Build team capabilities around prompt safety AI agent best practices and quality assurance.

• Partner with senior staff to develop learning programs in AI literacy humanintheloop design and prompt engineering.

• Contribute to a highperformance experimental datadriven culture within Trust Review Operations.

Core Responsibilities:

Prompt Design Testing & Optimization

• Design evaluate and iterate on prompts for generative and classification models supporting moderation risk detection case summarization and reviewer assistance.

• Conduct complex promptbased investigations to diagnose model behavior failure modes and quality issues.

• Establish frameworks for evaluating AI outputs across accuracy bias safety and consistency.

AIDriven Case Resolution & Risk Mitigation

• Integrate AI tooling into Trust Operations workflows to support scalable and consistent resolution of highrisk cases.

• Develop mitigation plans for model errors and propose longterm improvements that reduce operational and platform risk.

Escalation & Incident Management for AI Behavior

• Serve as the Trust Operations escalation point for issues involving AI output quality hallucinations override rates and misclassifications.

• Lead initiatives to prevent AIdriven escalations and strengthen model governance.

• Create and enforce rootcause and intervention frameworks specific to model performance.

Policy & Regulatory Alignment

• Ensure AIgenerated outputs comply with platform policies MDSS safety standards and international regulations (e.g. DSA synthetic media rules).

• Collaborate with Policy and Engineering teams to identify and mitigate emerging compliance risks.

Feedback Integration & Model Improvement

• Lead feedbackcollection programs focused on AI output quality partnering with Policy Operations Data Science Engineering and human reviewers.

• Translate reviewer insights into actionable model refinement requirements and product changes.

Data Analysis & Experimentation

• Analyze model and prompt performance data to generate insights and influence improvements.

• Execute experiments measure impact validate results and present findings to leadership.

• Partner with Data Science to build recurring model performance dashboards and reports.

Trend & Behavior Analysis

• Monitor trends in user behavior harmful content types and classifier drift to anticipate new risk patterns.

• Influence roadmap decisions by identifying where AI or automation can enhance detection routing or review efficiency.

Qualifications :

Basic Qualifications

• Bachelors degree or equivalent experience in Data Science Policy AI Engineering or related field

• 1 years experience designing debugging / optimizing prompts for LLMs or content moderation models.

• 5 years experience in Trust & Safety content moderation quality engineering policy or related domains.

• 2 years experience using data tools (e.g. SQL and python) to evaluate model and prompt performance.

Preferred Qualifications

• Strong written communication skills with the ability to produce clear structured prompt instructions.
• Ability to analyze model outputs and identify behavioral patterns risks and improvement opportunities.
• Experience successfully implementing Decision Quality solutions / frameworks 

• Prior experience working with classification models generative AI systems or humanintheloop workflows.

• Understanding of Trust & Safety policies global regulations (e.g. DSA) and safety standards.

• Experience partnering directly with Product Engineering or Data Science teams on AI feature development.

• Familiarity with evaluation metrics such as precision recall FPR FDR and adversarial testing.

• Ability to influence strategy through experimentation datadriven insights and crossfunctional leadership.

Suggested Skills:

• Analytical Excellence

• Creativity & Adaptability

• Data Interpretation

• Leadership & Coaching

• Problem-Solving

• Written Communication 

Additional Information :

Global Data Privacy Notice for Job Candidates

Please follow this link to access the document that provides transparency around the way in which LinkedIn handles personal data of employees and job applicants: Work :

No

Employment Type :

Full-time