Teams at Weekday, Inc.

Reviews and compares AI chatbot responses using predefined criteria for accuracy, relevance, completeness, clarity, consistency, and quality. Documents evaluation guidelines, analyzes workflows and data, identifies recurring issues, prepares reports, tracks quality metrics, and collaborates with project teams. This fully remote, 16-week contract requires 8 hours per day, five days per week, with Pacific Time overlap and possible weekend work.

Evaluate educational AI conversations and generated responses for accuracy, relevance, completeness, clarity, and logic. Conduct research and fact-checking, synthesize information, annotate errors, provide evidence-based feedback, and create training data examples to improve AI models. The role requires reviewing genuine Gemini conversation history, submitting an exported JSON file, and working full-time remotely for a 16-week contract with PST overlap.

Design and validate complex engineering simulation problems for training and evaluating AI models and coding agents. Develop Python-based simulation workflows, automated tests, reference solutions, and grading systems across electrical, mechanical, and aerospace domains. Analyze AI execution logs and failure modes, validate physical plausibility and numerical convergence, refine benchmarks, and collaborate with engineering and AI research teams. This remote contractor role requires approximately 40 hours weekly, Pacific Time overlap, and weekend on-call availability.