Mercor is looking for a Bilingual Spanish STEM Expert with experience in biology / physics / chemistry theory and problem-solving to develop and refine high-quality reasoning questions that evaluate AI models. Your knowledge in biology / physics / chemistry will ensure the accuracy, rigor, and instructional quality of these test items. You will create and evaluate Spanish/English prompts and responses, ensuring scientific precision while maintaining clear, natural Spanish phrasing and alignment with English where needed.
Job Details
Job Details
- Design and Optimize STEM-Based Prompts (Bilingual): Create detailed prompts in Spanish and/or English with multiple constraints and scientific instructions.
- Define and Document Evaluation Standards: Establish high-level expectations for correct responses in STEM contexts, and develop comprehensive rubrics that account for scientific rigor and—when in Spanish—linguistic clarity and appropriate academic tone.
- Conduct Model Testing and Grading (Bilingual): Run prompts through models and assess preliminary outputs against expectations for scientific accuracy, reasoning quality, and clarity, comparing Spanish vs. English where needed.
- Support Benchmarking and Quality Assurance: Collaborate in QA review processes to ensure prompt tasks and rubrics meet scientific rigor, maintaining consistency and reliability across Spanish-language benchmarks before integration into official benchmarks.
- Native-level fluency in Spanish (written) with strong reading/writing ability in English
- BS or BA in Biology / Physics / Chemistry
- Familiarity with undergraduate-level biology / physics / chemistry topics
- Strong writing and critical thinking skills
- Ability to work independently and meet deadlines
- 2+ years of experience in teaching, research, or an applied STEM discipline field
- Complete an AI-led interview (around 15 minutes)
- Complete a 45-minute written assessment that will guide you through writing rubrics
- If selected, you will be invited to work on the project
- Expect to contribute at least 20 hours per week
- Expect a commitment of around 1 month
- You’ll be working in a structured project environment with clear goals and tools