Duration: Nov (short-term contractor). Possibility for extension
Commitment: Part-time or Full-Time (10–40 hrs/week)
Location: SF in-office or Remote (must be a US citizen)
Compensation: $30-$50/hour, open for discussion
Other Perks: Direct touchpoints with AI researchers
Next step: Apply via the link below, and we will invite select candidates for interviews
July AI is building a data marketplace that is focused on serving the needs of humans. Our mission is to increase economic opportunities in the age of AI. We are based in San Francisco, backed by top-tier investors like Basis Set, Night Capital, SV Angel, Olive Capital.
About the Role
We’re looking for writers, storytellers, and creative thinkers eager to apply their craft in ways AI can’t replace - and to reinvent their skills for the AI-fueled future. By using your language, rhetoric, and imagination skills, you’ll help tackle one of the most important challenges in technology: AI safety.
This role is called AI red teaming. You will create adversarial conversations/scenarios by writing a series of prompts that are fed into AI models to see how they respond. The goal with these conversations is to try and trick, confuse, or jailbreak the system - in other words, get the AI model to produce an unsafe or unintended response.
Your prompts will be used to improve the safety of a frontier research lab’s newest AI model. This is an opportunity to pivot into the AI field, and make real-world impact by helping build the safety infrastructure for a leading AI model - creating safer technology for society as a whole.
We want to onboard contributors as soon as possible, but the official project will run for 6-8 weeks from mid-October to November.
Who we want
- Ideal background includes (but not limited to):Creative writer
- Cybersecurity / Red teamer
- Prompt Engineer
- Journalist / Editor
- Copy Writer
- Designer
- Marketer
- And other talented creatives who enjoy pushing the limits of AI and have the potential to create high quality stories/prompts
- Bonus skills:Ability to think critically, craft storylines/characters, and able to effectively understand and communicate with AI models in written form
- Interested in AI safety and ethics
- Keen to acquire skills in AI
Core responsibilities
- Craft adversarial test prompts / stories that stress test the AI model
- Interpret / understand AI model behavior
- Understand and follow the exact criteria for each attack and adhere to any safety or content rules we provide so your tests are relevant
- Document your findings: For each test, record the steps to reproduce it, how serious the problem is, and any ideas for fixing or reducing the issue
- Keep the July AI team updated with findings throughout the engagement
- Adhere to NDAs, ethics, and safety guidelines
Requirements
- Highly recommended for applicants unfamiliar with AI red teaming: Complete the “Red Team - Beginner” module. This will provide a solid introduction to red teaming and make it easier to create strong sample submissions
- Need to complete and submit at least 5 sample red team conversations on our platform (the instructions are in the application below)
- These sample submissions don’t have to all be successful. We’re mainly looking for creativity, adaptability, and persistence (more detail under “Tips to create a good red team prompt”)
- You may submit multiple attempts on the same challenge
- Excellent written documentation skills
- Availability during Oct–Nov; state earliest start date and weekly hours
Tips to create a good red team conversation
- Each sample submission should consist of multiple prompts that produce a single narrative/story. The overarching goal is to use this narrative to trick the AI model into providing the desired response outlined in each challenge
- Creativity: Ability to write a variety of different and original storiesMake sure all your red team/attack prompts are original ideas. Craft a cohesive and creative story that tricks the AI model into providing the desired output
- Each storyline has a persona (whether it’s you or a made-up character)
- Ensure the prompts and stories are about a real person/scenario
- Do not feed any gibberish into the model
- Adaptability and Persistence: Able to consistently adjust attacks based on the AI model’s responseThese prompts should demonstrate that you are learning from the AI’s defenses and refining your strategy
- Some of the best attempts are the ones where each prompt demonstrates a clear, logical progression that builds on the previous prompt
- Make sure there is an intention behind each prompt
- Writing Reproducible Prompts: Make sure you are able to explain your thought process behind the prompts/stories you are feeding into the modelYou can do this under the “Annotation” box in the sample submissions
- Ideal if the model outputs a detailed response that satisfies the topic requirements
If there are any questions, please reach out to info@gojuly.ai
