San Jose, California
•
Yesterday
Design refine and test prompts to improve LLM performance across various use cases Collaborate with product engineering and business teams to translate requirements into prompt workflows Develop prompt libraries templates and reusable components for internal teams Conduct evaluations AB testing and performance monitoring of generative AI outputs Finetune LLMs or work with model APIs to improve reliability and contextual accuracy Document prompt strategies best practices and optimization guidelin
Easy Apply
Third Party, Contract
Depends on Experience














