US RemoteDescription:
The role involves collaborating closely with Engineering and Production teams to comprehend their inquiries and requirements, subsequently devising strategies for optimizing solutions through prompt creation and engineering methodologies.
Responsibilities include crafting and refining prompts, constructing characters (e.g., Character.ai), and employing a suitable blend of tools and frameworks for assessing both prompts and models.
The position entails delivering comprehensive reports on prompts and conducting quality analyses to gauge their impact on key performance indicators (KPIs) for conversational agents. Additionally, providing Engineering and Production teams with thorough insights into the process, generated data, and evaluation metrics is vital.
Qualifications:
- Fluency in English
- Familiarity with LLMs (e.g., ChatGPT)
- Familiarity with using engineering tools, command lines, and running basic software programs
- Experience with writing prompts for different use cases
- Experience with evaluation, annotation, and data analysis for language/text tasks
- Experience with refining general-purpose LLMs for specific applications
- Experience with natural language processing, text mining, conversational AI, or leveraging large language models
- Experience with engineering, testing, and evaluating the performance of AI prompts
