Crossing Hurdles is seeking a Bilingual Portuguese Generalist Evaluator Expert. The role involves creating detailed prompts and evaluating AI model outputs for accuracy and cultural alignment in Portuguese, while collaborating on quality assurance processes.
Responsibilities:
- Create detailed prompts in Portuguese and/or English with multiple constraints and clear instructions, ensuring natural phrasing and real-world relevance for Portuguese-speaking users
- Develop high-quality Portuguese/English prompt–golden answer pairs to train and evaluate advanced language models
- Define evaluation standards and build comprehensive rubrics aligned with Portuguese linguistic nuance, tone, and cultural conventions
- Run prompts through AI models and assess outputs for accuracy, fluency, and cultural alignment in Portuguese, comparing results against English when required
- Collaborate in QA review processes to ensure consistency, rigor, and reliability across Portuguese-language benchmarks
- Deliver structured, high-quality written work within project timelines
Requirements:
- Native-level fluency in written Portuguese with strong reading and writing proficiency in English
- BS or BA from a reputable institution (completed or in progress)
- Strong writing, analytical, and critical thinking skills
- Ability to work independently and meet deadlines in a remote environment
- Significant familiarity with ChatGPT or similar AI tools
- Must able to reliably produce culturally accurate, Brazil-specific Portuguese content