Akan Language Expert

About the Role

The role requires a high level of attention to detail, as well as the ability to work independently in a remote setting. You will be part of a team that is dedicated to enhancing the capabilities of AuraOne's AI technologies, and your contributions will have a direct impact on the company's mission.

AuraOne is committed to using human evaluation to enhance its AI capabilities, and this role is a key part of that effort. By working with the company, you will have the opportunity to be at the forefront of AI development and to contribute to the creation of more accurate and effective models.

What You Will Do

• Evaluate Akan language evaluation model outputs against a versioned rubric and assign severity tags.
• Compare paired responses and pick the stronger answer with a written rationale.
• Label hallucinations, instruction-following failures, and unsafe content with structured tags.
• Capture ambiguous prompts and route them back to the program team for rubric updates.
• Maintain reviewer-quality scores by calibrating against gold-standard examples each week.
• Document recurring failure modes so the modeling team can target them in the next training run.
• Audit batches for rubric consistency and report drift to the program lead.
• Propose rubric clarifications after spotting recurring failure modes.
• Collaborate with the program team to improve the overall quality of the evaluation process.

What We Are Looking For

• Prior evaluation, annotation, or human-rater experience on Akan language evaluation or adjacent content.
• Comfort applying multi-page rubrics consistently across long batches.
• Clear written reasoning that names the issue and the rubric clause being applied.
• Strong attention to detail and the ability to flag when a prompt itself is the problem.
• Reliable async availability for at least 10 hours per week.
• Experience with digital tools and platforms used for evaluation and annotation.
• Ability to work in a fast-paced environment and meet deadlines.
• Strong communication skills and ability to collaborate with remote teams.

Nice to Have

• Background in linguistics, content moderation, or trust & safety review.
• Experience with inter-rater agreement metrics and calibration cycles.
• Domain expertise that lets you spot subject-matter errors automated checks miss.

Benefits and Perks

• Competitive hourly rate confirmed after the interview process.
• Opportunity to work with a leading company in the AI development space.
• Remote work arrangement with flexible scheduling.
• Access to cutting-edge technologies and tools.
• Professional development opportunities in the field of AI evaluation.
• Collaborative and dynamic work environment.
• Recognition and rewards for outstanding performance.

• When applying, make sure to highlight your experience in evaluation, annotation, or human-rater roles, especially in Akan language or similar contexts.
• Be prepared to provide examples of your work, including any experience with rubrics, calibration, and feedback provision.
• Showcase your ability to work independently in a remote setting and manage your time effectively.
• Emphasize your attention to detail and ability to identify and flag issues with prompts or outputs.
• Consider creating a portfolio that demonstrates your skills in evaluation and annotation, including any relevant certifications or training.
• During interviews, be ready to discuss your understanding of AI model outputs, your experience with digital tools, and your approach to providing structured feedback.
• When negotiating salary, research the market rate for similar roles and be prepared to discuss your expectations based on your experience and qualifications.