Outlier AI - AI Training tasks
Computer Code ProgrammingComputer Programming Coding
Engaged in an ongoing AI model and agent evaluation project focused on computer code and programming tasks, model stump. Responsibilities include prompt engineering, reviewing, annotating, and rating AI-generated code outputs across multiple programming languages, assessing correctness, efficiency, and adherence to best practices. Evaluated agentic workflows and multi-step reasoning tasks to identify model strengths and failure modes. Maintained high-quality annotation standards by following detailed rubrics and guidelines, contributing to the improvement of LLM coding capabilities
Engaged in an ongoing AI model and agent evaluation project focused on computer code and programming tasks, model stump. Responsibilities include prompt engineering, reviewing, annotating, and rating AI-generated code outputs across multiple programming languages, assessing correctness, efficiency, and adherence to best practices. Evaluated agentic workflows and multi-step reasoning tasks to identify model strengths and failure modes. Maintained high-quality annotation standards by following detailed rubrics and guidelines, contributing to the improvement of LLM coding capabilities
2026 - Present