Agentic AI - Super reviewer / Tech Lead
Responsible for designing comprehensive evaluation frameworks and grading rubrics to measure LLM performance in software engineering. I develop complex programming benchmarks and perform rigorous peer reviews of evaluation datasets to ensure high-quality training signals. • Consulting for a top-tier AI companies from the US • Improving LLM-generated applications. • Implementing a scalable evaluation framework for benchmarking AI models. • I provide consulting services in developing new innovative web technologies, focusing on selecting the right tools, designing implementation strategies, and effectively scaling applications. I analyze business and technical requirements, propose optimal solutions, and guide the implementation to ensure the highest quality and security standards.