About the Role:
- You will serve as a subject matter expert on AI model evaluation projects.
- You will design rigorous chemistry prompts and assess model outputs at an expert level.
What You'll Do:
- Create and evaluate complex chemistry prompts across multiple chemistry domains.
- Apply adversarial prompting strategies to induce and document model reasoning errors.
- Critically assess the accuracy, depth, and scientific validity of AI-generated responses.
What We're Looking For:
- PhD in Chemistry or a closely related field.
- Graduate-level expertise across multiple areas of Chemistry.
- Permanently based in the US with prior hands-on experience in AI data annotation or RLHF.
The posting does not specify a company name.
The company is a specialized AI evaluation and training platform focused on advancing the capabilities of AI models in scientific domains. It employs experts across various fields to rigorously test and improve AI reasoning and accuracy, fostering a culture of deep technical collaboration and flexible contribution.