Note: The job is a remote job and is open to candidates in USA. Crossing Hurdles is seeking a Generalist – English to assess AI-generated responses and provide feedback to enhance model quality. The role involves evaluating reasoning, tone, and factual accuracy while supporting the improvement of large language models.
Responsibilities
- Assess AI-generated responses across a wide range of topics
- Provide structured human feedback to improve model reasoning and response quality
- Evaluate reasoning quality, tone, and factual accuracy
- Support the improvement of large language models (LLMs) to ensure accurate, well-reasoned, and human-aligned outputs
Skills
- Strong written English skills
- Strong analytical thinking and attention to detail
- Ability to evaluate reasoning quality and factual accuracy across diverse topics
- Comfortable working under a flexible full-time or part-time contract model
Company Overview