About OpenTrain
OpenTrain is the centralized, open platform where AI training and data-labeling freelancers find work, consolidate opportunities across platforms, and build a unified AI training portfolio they control. We make specialized AI training work easier to track, apply for, and grow into a durable freelance career.
About this role
OpenTrain is recruiting for an ML Evaluation Data Analyst to support benchmark-driven evaluation of real-world machine learning systems. You will analyze structured and unstructured data from training, inference, and evaluation pipelines, assess model outputs and metrics, investigate failure modes, and help improve the reliability of advanced AI systems through rigorous, reproducible analysis.
What you will do
Analyze datasets generated by machine learning training, inference, and evaluation workflows. Define, compute, and validate metrics used to assess model performance and behavior. Investigate data distributions, edge cases, model outputs, and benchmark failures. Use Python and SQL to analyze data, produce reports, and support evaluation workflows. Validate data quality, consistency, and correctness across datasets and experiments. Create clear analytical artifacts and reproducible analysis workflows. Collaborate with ML engineers and researchers on challenging, real-world evaluation scenarios.
Required skills
At least three years of experience as a data analyst or analytics-focused engineer is required. Candidates should have strong Python proficiency for data analysis, solid SQL experience with relational datasets, and experience analyzing ML outputs and evaluation metrics. Strong statistical understanding, analytical reasoning, and the ability to work with large, complex datasets are important. Candidates should also be able to write clean, readable, well-documented analytical code and communicate clearly in spoken and written English.
Work arrangement
This is a remote contractor assignment available in India, Pakistan, Nigeria, Kenya, Egypt, Ghana, Bangladesh, Turkey, Brazil, and Mexico. The role requires at least four hours per day and 20 hours per week, including four hours of overlap with PST, for a three-month contract that may be adjusted based on engagement.
Why work with OpenTrain
OpenTrain gives freelancers one place to manage AI training opportunities instead of rebuilding proof of work on every platform. A stronger OpenTrain profile helps you show credible experience, discover roles that match your skills, and turn AI training and data-labeling work into a long-term portfolio.