SWE AI Code Reviewer
Part-Time Contractor
- Collaborated with multiple AI firms to evaluate and improve LLM-generated code, boosting output accuracy and efficiency.
- Designed and refined prompt templates to raise LLM alignment scores and user satisfaction across production workflows.
- Delivered code reviews that maintained a 4.0+ quality rating and earned top-tier evaluator recognition.
- Performed static analysis, debugging, and refactoring to produce production-ready code meeting industry standards.
- Ensured accurate metrics, reproducible results, and reliable model comparisons across multiple frameworks and languages.