AI Technical Consultant, LLM Safety Evaluation, Digital Impact Division, Digital Guardrails, Home-based, Valencia, Spain, 6 Months and 20 days #596213

UNICEF works in over 190 countries and territories to save children’s lives, defend their rights, and help them fulfill their potential, from early childhood through adolescence.

At UNICEF, we are committed, passionate, and proud of what we do for as long as we are needed. Promoting the rights of every child is not just a job – it is a calling.

UNICEF is a place where careers are built. We offer our staff diverse opportunities for professional and personal development that will help them reinforce a sense of purpose while serving children and communities across the world. We welcome everyone who wants to belong and grow in a diverse and passionate culture., coupled with an attractive compensation and benefits package.

Visit our website to learn more about what we do at UNICEF.

• Prepare, clean and structure the agreed test prompt set.
• Conduct extensive testing of agreed prompts across multiple LLM providers and configurations, and curate the most informative model responses for expert review.
• Run evaluations under different approved safety/content-filter configurations and document how these settings affect model behaviour.
• Capture model responses and relevant test metadata.
• Troubleshoot API, model, safety-filter or platform issues.
• Develop and maintain code to call commercial LLM APIs and, where required, deploy and interact with open-source models for evaluation.
• Conduct targeted reviews of state-of-the-art child-safety and AI-safety research to identify relevant prompts, failure modes and emerging risks.
• Organise outputs into a simple format for expert review.
• Support simple rating, ranking and reviewer comments.
• Capture review results in a structured, exportable format.
• Iterate the prototype based on expert feedback.
• Participate in communication with reviewers, collect feedback on both model behaviour and the review process, and refine the testing/review infrastructure accordingly.
• Support re-testing when experts identify new failure modes, ambiguities or edge cases.
• Help translate expert feedback into new or refined test cases.
• Maintain a clean, versioned prompt-response dataset.

If you would like to know more about this consultancy, please review the complete Terms of Reference here:  TOR AI Technical Consultant LLM Safety Evaluation.pdf

• Education: Advanced university degree (Master’s or equivalent) in computer science, artificial intelligence,

• Work Experience: Minimum five years of relevant professional experience in AI/ML, software engineering,

• Skills:

UNICEF’s Core Values of Care, Respect, Integrity, Trust and Accountability and Sustainability (CRITAS) underpin everything we do and how we do it. Get acquainted with Our Values Charter: UNICEF Values

UNICEF promotes and advocates for the protection of the rights of every child, everywhere, in everything it does and is mandated to support the realization of the rights of every child, including those most disadvantaged, and our global workforce must reflect the diversity of those children. The UNICEF family is committed to include everyone, irrespective of their race/ethnicity, disability, gender identity, sexual orientation, religion, nationality, socio-economic background, minority, or any other status.

UNICEF encourages applications from all qualified candidates, regardless of gender, nationality, religious or ethnic backgrounds, and from people with disabilities, including neurodivergence. We offer reasonable accommodation for persons with disabilities. throughout the recruitment process. If you require any accommodation, please submit your request through the accessibility email button on the UNICEF Careers webpage Accessibility | UNICEF. Should you be shortlisted, please get in touch with the recruiter directly to share further details, enabling us to make the necessary arrangements in advance.

UNICEF does not hire candidates who are married to children (persons under 18). UNICEF has a zero-tolerance policy on conduct that is incompatible with the aims and objectives of the United Nations and UNICEF, including sexual exploitation and abuse, sexual harassment, abuse of authority and discrimination based on gender, nationality, age, race, sexual orientation, religious or ethnic background or disabilities. UNICEF is committed to promote the protection and safeguarding of all children. All selected candidates will, therefore, undergo rigorous reference and background checks, and will be expected to adhere to these standards and principles. Background checks will include the verification of academic credential(s) and employment history. Selected candidates may be required to provide additional information to conduct a background check, and selected candidates with disabilities may be requested to submit supporting documentation in relation to their disability confidentially.

• An up-to-date TMS profile and curriculum vitae (CV)
• Cover letter
• A separate financial proposal (only acceptable in the format of the linked template)  Financial proposal xxx6883.docx

Remarks:   If the TOR or financial proposal documents are not visible on certain recruitment platforms, please visit our official page Vacancies | UNICEF Careers

UNICEF does not charge a processing fee at any stage of its recruitment, selection, and hiring processes (i.e., application stage, interview stage, validation stage, or appointment and training). UNICEF will not ask for applicants’ bank account information.

All UNICEF positions are advertised, and only shortlisted candidates will be contacted and advance to the next stage of the selection process.

Additional information about working for UNICEF can be found here.

Advertised: 09 Oct 2026 Romance Daylight Time
Applications close: 15 Oct 2026 Romance Daylight Time

Back to search results Apply now Refer a friend