Independent Red Teaming and AI Safety Evaluation

Job not on LinkedIn

🔥 0 minutes ago

🇰🇪 Kenya – Remote

⏳ Contract/Temporary

🟡 Mid-level

🟠 Senior

🤖 Artificial Intelligence

👻 Ghost score 15%

What it means: the chance that no one is really hiring for this job.How to read it: 60% or higher means we think this is a ghost. Lower scores are less of a worry.How we score it: age, reposts, open roles vs team size, how fast jobs close, and whether pay is listed.Fine print: an estimate from public data, not a judgment of the company. Real jobs can score high, so treat it as a hint, not a fact.

Apply Now

Find Similar Remote Jobs

Girl Effect

WebsiteLinkedInAll Job Openings

51 - 200 employees

🤝 Non-profit

📚 Education

🌍 Social Impact

Non-profit • Education • Social Impact

Girl Effect is a creative non-profit empowering girls to change their lives. Started by the Nike Foundation, we are experts in media, tech, brand, and international development, using a unique mix of skills to solve global problems in innovative ways. Operating in marginalised and vulnerable areas, we create engaging content for young people through various formats such as apps, TV dramas, and magazines. With our partners, we currently reach 50 million people across Africa and Asia, focusing on helping girls express themselves, value themselves, and build essential relationships.

📋 Description

• Conduct a focused and independent red-team evaluation of WAZZII’s girl-facing generative AI capability • Identify safety, safeguarding, clinical and technical vulnerabilities • Test whether the system recognises and safely escalates relevant risks • Assess whether existing evaluations and controls reflect real-world use • Produce reproducible, machine-readable and rerunnable test cases • Rank findings by severity, likelihood and potential impact • Provide practical, prioritised remediation and future-evaluation recommendations • Review evaluation frameworks, red-line policies and escalation protocols • Co-scope scenario taxonomy, severity rubric and responsible-disclosure protocol • Conduct adversarial and realistic non-adversarial testing in staging • Test clinically incorrect or harmful health advice, safeguarding escalation, jailbreaks, prompt injection, policy circumvention and age-inappropriate content • Test English, Kiswahili and Sheng, including code-switching patterns • Stress-test human escalation and moderation pathways • Produce an inception note and test plan by week 3 • Produce a severity-ranked findings report with reproducible test cases by week 8 • Deliver a leadership briefing and prioritised recommendations by week 10 • Participate in weekly progress meetings • Maintain a shared delivery tracker and risk register • Use secure communication and evidence-sharing channels • Escalate critical issues immediately • Protect access credentials and evaluation materials • Manage personnel and delivery approach independently

🎯 Requirements

• Independent organisation or specialist consultancy • Independence is a mandatory condition; bidder must not build, operate, or commercially benefit from the systems evaluated • No current contract to build or operate the system being evaluated • No commercial interest in the evaluation achieving a particular outcome • Disclosure of current or previous relationships with Girl Effect’s AI, platform or technology suppliers, including relevant relationships during the previous 24 months • Disclosure of tools or models being evaluated in which the bidder has a financial interest • Experience independently red-teaming deployed AI systems • Experience with conversational AI, retrieval-augmented generation and multi-turn systems • Experience in health, safeguarding-sensitive or other high-risk contexts • Experience with adolescent or youth-facing digital services • Strong knowledge of AI safety, responsible AI and model evaluation • Ability to build automated, machine-readable and rerunnable testing harnesses • Understanding of human escalation and moderation workflows • Ability to test English, Kiswahili and Sheng directly or through a credible quality-controlled approach • Experience working in Kenya, Africa or comparable Global South contexts • Strong security, confidentiality and responsible-disclosure practices • Excellent analytical, technical-reporting and leadership-presentation capability • Proposed team must include named individuals with AI evaluation, technical, safeguarding and language expertise • Separate technical and financial proposals, maximum 10 pages • Three client references • One redacted example of a relevant findings report • Successful bidder subject to due diligence, reference, safeguarding, information-security and compliance checks • Successful bidder must comply with Girl Effect’s code of conduct, safeguarding and anti-fraud requirements • No material subcontracting without prior written approval • Proposals must remain valid for 90 days from the submission deadline

🏖️ Benefits

• Girl Effect will provide approved access to the staging environment • Programmatic access to the conversational endpoint where available • Relevant documentation and evaluation materials • Named technical, safeguarding and programme focal points • Consolidated feedback on deliverables • Payments linked to satisfactory completion and written acceptance of agreed deliverables • Reasonable expenses approved in writing in advance may be reimbursable • Warranty period for correcting defects in accepted deliverables at no additional cost, as proposed • Opportunity to work remotely; no in-country presence required • Girl Effect will own foreground intellectual property created specifically under the engagement

📊 Check your resume score for this job

Improve your chances of getting an interview by checking your resume score before you apply.

Upload Resume