I'm a Staff Software Engineer at Uber with ten years of experience in software design and development. My expertise lies in building scalable systems, particularly in areas like Generative AI applications and config-driven automation.
A centralized prompt engineering toolkit to help developers build better applications powered by LLMs. This toolkit provides tools and best practices for crafting effective prompts, managing prompt versions, and evaluating the performance of LLM-based features. Furthermore, there’s a need for version control, collaboration, and robust safety measures (hallucination checks, standardized evaluation framework, and a safety policy) to ensure responsible AI usage.
