ML Challenge Task Auditor

Put your applied ML rigor to work judging machine learning tasks. You review experiment design, model selection and evaluation methods, and write clear feedback against a rubric. This is about experimental ML, not building LLM apps or MLOps.

What you will do

• Review applied machine learning tasks for quality, correctness and methodological rigor.
• Assess experiment design, model-selection reasoning and evaluation methodology.
• Check ML claims against the evidence and reproduce results.
• Write clear, rubric-based feedback on each task.

What you need

• 3+ years of hands-on applied or experimental ML: experiment design, model selection, hyperparameter tuning and evaluation methodology.
• A strong grasp of data-quality rigor, including leakage detection, metric gaming and train, test and cross-validation hygiene.
• Proficiency with standard ML frameworks such as PyTorch, TensorFlow, scikit-learn and XGBoost.

Nice to have: competition or benchmark experience (for example Kaggle), graduate research or publications in applied ML, and prior task-grading or peer-review experience.