Election Neutrality | Safety Project
WFA Digital Insight
Vetto’s Election Neutrality Safety Project pulls together two niche worlds: political debate expertise and AI safety evaluation. Unlike generic data‑labeling gigs, this role asks contributors to inhabit a specific political persona, sustain a believable multi‑turn conversation, and then judge the model’s ability to stay balanced under pressure. The focus on international political discourse means you’ll be testing AI on topics that often spark heated disagreement, making the work both intellectually demanding and socially relevant. Vetto stresses strict compliance – no AI tools are permitted at any stage – so the assessment rests entirely on human judgment. If you thrive on lively debate, can separate personal bias from the assigned viewpoint, and enjoy detailed, instruction‑heavy tasks, this project offers a rare chance to influence the ethical direction of emerging conversational agents.
Job Description
## About Vetto AI
Vetto AI connects qualified professionals to strategic Artificial Intelligence projects. Our work supports the development of safer, more reliable, and more responsible AI systems through high-quality human evaluation data.
## About the project
We are opening a new opportunity for the Safety Project — Election Neutrality, a project focused on evaluating how AI systems behave in politically sensitive conversations.
The goal of this project is to assess whether AI can remain neutral, balanced, and responsible during multi-turn interactions with users who express different political opinions, positions, and perspectives.
For this project, we are looking for people who regularly engage in political discussions — whether at the dinner table, with friends, at work, online, or in other real-life contexts — and who can draw from their own debate experience to create realistic political interactions with AI.
The project will involve scenarios related to international political discussions, where contributors will role-play users with specific perspectives and evaluate how the AI responds.
## Main responsibilities
As a contributor, you will be expected to:
- Understand the political context and perspective you are expected to role-play
- Conduct a realistic multi-turn conversation with the AI
- Defend or express the assigned political position naturally, as a real person would
- Justify your evaluation using specific turns and evidence from the interaction
- Identify whether the AI remained neutral, balanced, and responsible when responding to political opinions under pushback
## What we are looking for
This role may be a good fit if you:
- Regularly engage in international political debates or discussions in real life
- Have experience defending a political position under disagreement or pushback
- Are interested in international politics, public debate, political discourse, or current affairs
- Can follow detailed instructions and long guidelines carefully
- Can evaluate AI responses objectively, even when the topic involves political disagreement
- Are able to separate your personal opinion from the assigned persona and evaluation criteria
## Requirements
To participate in this project, contributors must:
- Have advanced or fluent English
- Be comfortable discussing political topics in a structured and professional way
- Be able to follow detailed project guidelines precisely
- Be able to complete realistic role-play based on assigned political scenarios
- Understand that using AI during the application process or during the project is strictly forbidden
## Important compliance requirement
The use of AI tools is strictly forbidden in both the application process and the project tasks.
This includes using AI to write application answers, translate messages, create conversation turns, draft evaluations, or produce justifications.
All work must be written by the contributor. If AI use is detected, the contributor may be removed from the selection process or from the project.
## Compensation
Brazil: R$ 100 per approved task
Other countries: $20 per approved task
Only approved tasks are eligible for payment. To increase the chances of approval, contributors must carefully follow the guidelines.
## Final note
This is a high-impact AI safety project focused on political neutrality. Your work will help evaluate how AI systems respond to users across different political perspectives, especially in realistic, multi-turn conversations where disagreement, persuasion, and pushback may occur.
How to Stand Out
- Record your conversations in plain text without any AI‑generated assistance; manual typing is mandatory.
- Highlight specific turn numbers when noting bias or neutrality in your evaluation form.
- Familiarize yourself with the political scenario before starting the chat to ensure a smooth role‑play.
- Proofread each submission for spelling and grammar; clean writing boosts approval chances.
- Mention any prior debate or political analysis experience in your application to stand out.
- Be prepared to explain how you kept personal views separate from the assigned persona during the interview.
- Review Vetto’s compliance rules carefully; any accidental AI usage will disqualify you.
This is a remote position listed on WFA Digital, the platform for professionals who work from anywhere. Browse more remote jobs across all categories.