- Design, develop, and enhance prompts for large language models to achieve targeted outcomes across multiple applications.
- Collaborate with data, technology, and product teams to understand project requirements and translate them into effective prompt strategies.
- Conduct thorough testing and analysis of prompt performance, including A/B testing, automated testing, and user feedback evaluation.
- Assess prompts for various LLMs and measure their effectiveness.
- Create and maintain a library of reusable prompt components and best practices.
- Keep abreast of the latest developments in prompt engineering and LLM capabilities.
- Write scripts and data pipelines to validate and enhance the quality of our models.
- Bachelorβs degree in Computer Science, Linguistics, or a related field.
- Proven experience in prompt engineering for large language models.
- Understanding of LLM architectures, capabilities, and limitations.
- Proficiency in Python, with experience in data analysis libraries (e.g., Pandas) preferred.
- Familiarity with machine learning frameworks (e.g., TensorFlow) is a plus.
- Knowledge of ethical AI principles and best practices for responsible AI development.
- Strong written and verbal communication skills in English.
TBD