MLE Bench – Data Analyst

• Analyze structured and unstructured datasets generated from ML training, inference, and evaluation pipelines.
• Define, compute, and validate metrics used to evaluate model performance and behavior.
• Investigate data distributions, model outputs, failure modes, and edge cases relevant to benchmark tasks.
• Write and run Python and SQL code to analyze data, create reports, and support evaluation workflows.
• Validate data quality, consistency, and correctness across datasets and experiments.
• Create clear, well-documented analytical artifacts and reproducible analysis workflows.
• Collaborate with ML engineers and researchers to design challenging, real-world evaluation scenarios for MLE Bench.

• Minimum 3+ years of experience as a Data Analyst or Analytics-focused Engineer.
• Strong proficiency in Python for data analysis.
• Solid experience with SQL and relational datasets.
• Experience analyzing ML outputs and evaluation metrics.
• Strong understanding of statistics and analytical reasoning.
• Ability to work with large, complex datasets and draw reliable insights.
• Experience writing clean, readable, and well-documented analytical code.
• Excellent spoken and written English communication skills.

RequiredAlso useful

Project and contracting process: Turing. Applications continue on the provider's website.