MLE Bench – ML Engineers

• Work with real-world ML codebases to support MLE Bench–style evaluation tasks.
• Build, run, and modify model training, evaluation, and inference pipelines.
• Prepare datasets, features, and metrics for ML benchmarking and validation.
• Debug, refactor, and improve production-like ML systems for correctness and performance.
• Evaluate model behavior, failure modes, and edge cases relevant to benchmark tasks.
• Write clean, reproducible, and well-documented Python code for ML workflows.
• Participate in code reviews to ensure high standards of engineering quality.
• Collaborate with researchers and engineers to design challenging, real-world ML engineering tasks for AI system evaluation.

• Minimum 3+ years of overall experience as a Machine Learning Engineer or Software Engineer (ML-focused).
• Strong proficiency in Python for machine learning and data workflows.
• Hands-on experience with model training, evaluation, and inference pipelines.
• Solid understanding of machine learning fundamentals (supervised/unsupervised learning, evaluation metrics, optimization).
• Experience working with ML frameworks (e.g., PyTorch, TensorFlow, JAX, or similar).
• Ability to understand, navigate, and modify complex, real-world ML codebases.
• Experience writing readable, reusable, and maintainable production-quality code.
• Strong problem-solving and debugging skills.
• Excellent spoken and written English communication skills.

RequiredAlso useful

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