Remote AI Trainer (Contract) - Code Benchmarking
Posted Updated
Description
Crossing Hurdles is seeking an AI Trainer for a remote, contract role. The position involves creating challenging software engineering tasks to stress-test advanced AI models, along with developing instructions, environments, solutions, tests, and evaluation criteria.
Ideal candidates have hands-on experience training and benchmarking AI systems, strong Python skills, and familiarity with at least one additional programming language.
Create realistic software engineering tasks that challenge advanced AI models. Develop task instructions, reproducible environments, reference solutions, tests, and evaluation criteria. Evaluate model-generated code and technical deliverables for correctness, robustness, and completeness. Identify issues involving implementation, debugging, dependencies, performance, testing, or reproducibility. Experience training, evaluating, benchmarking, or improving AI systems. Proficient in Python. Experience with at least one more language (e.g., Java, JavaScript, TypeScript, Rust, C++, C#, Go). Knowledge of software design, debugging, testing, version control, and dependency management.Skills
Sign in to read and join the discussion.