Description:We are seeking a Prompt Engineer with a strong foundation in data science and quality analysis to support evaluation and improvement of large language and multimodal models at a leading tech company.
In this role, you will craft, refine, and test prompts to guide generative AI systems while working cross-functionally to identify issues in model behavior.Ideal candidates will have prior experience in prompt design, applied data science (Python, SQL, or similar), and qualitative assessment of AI responses for quality and correctness.
Key Success Factors:Prompt Engineering Expertise: Demonstrated ability to craft and iterate prompts for LLMs and multimodal systems to achieve targeted behaviors or outputs.Data Analysis Skills: Experience using basic data science techniques (e.g., Python, SQL, pandas) to analyze model behavior or quality metrics.Quality Review Mindset: Familiarity with evaluating AI-generated outputs against quality standards (e.g., accuracy, safety, diversity, bias).Prior hands-on experience in analyzing the output of large generative models like GPT-4, Gemini, or Claude.