Job Description
Shape the next generation of AI models by reviewing and enhancing outputs generated by cutting-edge large language models (LLMs). Your expertise in statistics, data analysis, and quantitative reasoning will ensure that model outputs are accurate, insightful, and aligned with rigorous academic and applied standards. This role blends technical fluency with high-precision annotation and offers the opportunity to influence how AI understands and communicates statistical concepts.
Use internal tools to evaluate AI-generated responses, especially in statistical, mathematical, and scientific domains. Analyze and improve AI outputs with a focus on statistical correctness, clarity, and pedagogical relevance. Curate, annotate, and refine datasets used in training and fine-tuning LLMs with statistical content. Identify edge cases, model limitations, and annotation inconsistencies related to statistical reasoning. Collaborate with AI researchers and engineers to iterate on feedback loops and model alignment strategies.
About Handshake
Handshake is building the future of human data for AI and partners directly with top AI labs to power large language model (LLM) training and evaluation.