Employer description & source details
AI Model Evaluation: Evaluate AI-generated outputs on data science, statistics, machine learning, experimentation, and quantitative analysis tasks. Problem and Prompt Development: Create challenging, well-defined prompts and technical problems that assess analytical reasoning and practical data science skills. Dataset Preparation: Prepare and validate relevant datasets for testing AI models across statistical and machine learning use cases. Reference Solution Development: Develop accurate reference answers, calculations, and analytical solutions to establish reliable evaluation benchmarks. Statistical Validation: Identify statistical errors, incorrect assumptions, flawed methodologies, and inappropriate interpretations of data. Quantitative Reasoning Assessment: Assess whether AI-generated solutions demonstrate sound mathematical reasoning, appropriate analytical methods, and evidence-based conclusions. Structured Feedback: Provide clear, actionable feedback highlighting errors, missing steps, and opportunities to improve the accuracy and reliability of AI-generated outputs. Quality Assurance: Validate analytical results, review solution consistency, and ensure that evaluation criteria are objective and reproducible. Technical Documentation: Explain statistical concepts, analytical approaches, and evaluation findings in a clear and structured manner. At least one year of professional experience at a well-established company in technology, finance, research, or a related field. At least part of the relevant professional experience should have been gained within the past three years. Foundational knowledge of data science, statistics, machine learning, and quantitative analysis. Strong analytical and problem-solving skills, with the ability to evaluate data-driven conclus
Extracted skills: python, sql, machine learning, artificial intelligence, data analysis, finance