Prompt engineering is the art of instructing large language models in a way that delivers the most nuanced and high quality outputs. It is a hybrid between programming, instructing, and iterative experimentation. As a research prompt engineer, your role would be to work with our finetuning researchers to help deliver the best results from our models. This will include but need not be limited to: building on existing prompting techniques, developing new prompting techniques, testing prompt effectiveness, documenting prompts, supporting prompt testing infrastructure, and running experiments using the prompts you help to develop. You will be engaged in creative and cutting-edge finetuning research that will improve the performance and safety of frontier models. Given that this is a nascent field, we ask that you share with us a specific prompt engineering project on LLMs that you're proud of in your application. Ideally this project should show off a complex and clever prompting architecture, or a systematic evaluation of an LLM's behavior in response to different prompts, or an example of using LLMs for a relevant ML task such as careful dataset curation and processing. There is no preferred task, we just want to see how you create and experiment with prompts. You can also include a short description of the process you used or any roadblocks you hit and how to deal with them, but this is not a requirement. Responsibilities
- Develop new, creative, and original prompting strategies for a wide range of research tasks relevant to our fine-tuning efforts.
- Build upon and improve existing prompting techniques to increase their effectiveness and efficiency.
- Test and assess the effectiveness of both existing and newly developed prompts.
- Create and maintain documentation of prompts and promote internal knowledge sharing.
- Help to create and maintain the infrastructure required for efficient prompt iteration and testing.
- Work with finetuning researchers to run experiments using the prompts you have helped create.
- Stay up-to-date with the latest research in prompt engineering and share knowledge with the team.
You may be a good fit if you
- Have extensive prior experience exploring and testing language model behavior.
- Have a high level familiarity with the architecture and operation of large language models.
- Have good communication skills and an interest in working with researchers on difficult prompting tasks.
- Have a creative hacker spirit and a love of puzzle solving.
- Have a firm grasp of programming in Python and experience with data structures.
Strong candidates may also have experience with
- Advanced degree in computer science, mathematics, statistics, physics, or a related technical field, or an advanced degree in a relevant non-technical field alongside evidence of programming experience.
- Research experience in machine learning, natural language processing, or a related field.
- Experience with large-scale model training and evaluation.
- Passion for making powerful technology safe and societally beneficial.
Deadline to apply:None. Applications will be reviewed on a rolling basis.