Own AI evaluation methods and operations for Figma's AI-powered experiences, defining quality dimensions and designing measurement frameworks.
Build and maintain evaluation frameworks, rubrics, golden datasets, and quality bars using human and automated approaches.
Produce clear readouts and dashboards to enable stakeholders to make confident shipping decisions.
Figma is on a mission to make design accessible to all, empowering teams to bring ideas to life through collaborative design and prototyping tools. With a growing team of passionate creatives and builders, Figma fosters a culture of growth and inclusivity.
Write prompts in Luxembourgish to test AI models and evaluate responses using a structured rating guide.
Identify areas for improvement in AI responses and provide accurate English translations.
Work remotely on a flexible schedule with competitive pay.
CrowdGen by Appen is a platform that connects freelancers to help improve AI models through data annotation and evaluation. It is part of a large global company with a diverse community of independent contractors working remotely.
Create and curate an evaluation suite of real-world tasks for frontier AI models.
Rigorously evaluate AI systems, analyze results, and communicate findings.
Improve evaluation processes and potentially build out standalone benchmarks.
Epoch AI is a research institute that investigates trends in machine learning and the economic consequences of AI. Our mission is to develop a comprehensive, publicly accessible knowledge base on AI that informs policymakers, industry leaders, and society at large.
Design and execute complex role-play evaluation scenarios simulating real customer support interactions in domains like travel and finance.
Evaluate AI-generated audio outputs using structured qualitative and quantitative metrics, focusing on accuracy, fluency, and task completion.
Audit conversational performance and contribute to the creation and refinement of high-quality, representative audio datasets.
Our partner company specializes in AI training and evaluation for conversational models, focusing on audio quality and real-world scenarios. As a freelance platform, they offer flexible remote work opportunities to language and evaluation specialists.