Role Overview We are looking for experienced Data Analysts (MLE Bench) to contribute to benchmark-driven evaluation projects focused on real-world machine learning systems. This role involves hands-on analytical work with production-like datasets, metrics, and ML outputs to help evaluate, diagnose, and improve the performance of advanced AI systems. The ideal candidate is comfortable working at the intersection of data analysis and machine learning, with strong analytical rigor and the ability to work with real datasets and ML evaluation workflows. What does day-to-day life look like? 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. Requirements 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.

About Turing

Turing is one of the world’s fastest-growing AI companies accelerating the advancement and deployment of powerful AI systems. Turing helps customers in two ways: Working with the world’s leading AI labs to advance frontier model capabilities in thinking, reasoning, coding, agentic behavior, multimodality, multilinguality, STEM and frontier knowledge; and leveraging that work to build real-world AI systems that solve mission-critical priorities for companies. Powering this growth is Turing’s talent cloud, an AI-vetted pool of 4M+ software engineers, data scientists, and STEM experts who can train models and build AI applications. All of this is orchestrated by ALAN—our AI-powered platform for matching and managing talent, and generating high-quality human and synthetic data to improve model performance. ALAN also accelerates workflows for model and agent evals, supervised fine-tuning, reinforcement learning, reinforcement learning with human feedback, preference-pair generation, benchmarking, data capture for pre-training, post-training, and building AI applications. Turing is based in San Francisco, California and has been profiled by Fast Company, TechCrunch, Reuters, Semafor, VentureBeat, Entrepreneur, CNBC, Forbes, and many others. Turing’s leadership team includes AI technologists from Meta, Google, Microsoft, Apple, Amazon, X, Stanford, Caltech, and MIT.