AI Evaluation Expert - FunctionCall

1. Responsible for the effect and quality evaluation, evaluation standards, and system construction of the large language model in the Function Call direction, and fully communicate and collaborate with the product and algorithm teams to deeply understand the evaluation requirements 2. Participate in various business research and analysis, formulate and organize evaluation plans, and be able to use data analysis and other methods to disassemble and analyze problems, locate various experience problems of the model, combine evaluation and multiple perspectives to provide solutions and optimization directions, and output valuable analysis reports to assist model iteration optimization 3. Deeply explore the capabilities of Function Call, combine the performance and expectations of mainstream models on the market, and explore more possibilities of Function Call.

1. Have experience in large model evaluation or related products 2. Have a certain code foundation and can execute scripts to process data 3. Have enthusiasm for work and a spirit of exploration, and be good at promoting work 4. Be able to write conclusion reports independently and assist in large model iterations 5. Past work experience related to Function Call is preferred.