Writer | $40/hr Remote

Crossing Hurdles is hiring a Generalist Evaluator Expert (Writer) on an hourly contract to help train and evaluate advanced language models. The role focuses on authoring high-quality prompt and golden-answer pairs and building rubrics to assess model outputs in consumer contexts.

• Author prompt–golden answer pairs to train and evaluate advanced language models.
• Create detailed prompts with multiple constraints and instructions.
• Establish expectations for correct responses in general consumer contexts and develop comprehensive rubrics.
• Run prompts through models and assess outputs against defined expectations.
• Collaborate in QA review processes to ensure prompt tasks and rubrics meet rigor and maintain consistency before integration into official benchmarks.

• Education: BS or BA from a reputable institution (completed or in progress).

• Strong writing and critical thinking skills.

• Ability to work independently and meet deadlines.

• Familiarity with ChatGPT or similar tools for personal decision-making or general interests.

• Experience in teaching or research preferred.

• Type: Hourly contract.

• Compensation: $35–$40 per hour.

• Location: Remote.

• Commitment: At least 20 hours per week.

• Application process: Upload resume, interview (15 minutes), submit form (about 20 minutes total).