Software Developer - LLM Training
As a Software Developer involved in LLM training at AfterQuery Expert, I designed and evaluated tasks using code-based environments for the purpose of AI model benchmarking. My primary focus was on constructing and testing terminal-based workflows within Docker and Bash/Linux systems. This work contributed directly to the evaluation and improvement of large language models through carefully crafted coding scenarios. • Designed evaluation tasks for code generation and execution. • Developed automated workflows for LLM performance assessment. • Implemented diverse coding scenarios to challenge AI comprehension. • Benchmarked and rated AI model outputs for accuracy and reliability.