Job Description

Qualified candidates must be located in one of the following locations due to position being ONSITE:

Los Angeles CA, Seattle WA, Redmond WA, Bellevue WA, Austin TX, New York NY , San Francisco CA and Menlo Park CA

**Polish*

**This role may involve potential exposure to graphic and/or objectionable content including but not limited to graphic images, videos and writings, offensive or derogatory language, and other potential objectionable material, i.e. child exploitation, graphic violence, self-injury, animal abuse, and other content which may be considered offensive or disturbing.

Ability to work with graphic and objectionable content.**

Top 3 must-have HARD skills:

• Fluent in Polish

• Very solid written and verbal *English* communication skills

• Excellent writing, communication and collaboration skills, with the ability to work effectively with cross-functional teams

• Experience with data annotation tools and techniques

• 2-3 Years of experience

• Technical background will be beneficial in quickly onboarding to the role of red teamer

  Good to have skills:

• Linguistic training/Media education/Content Moderation

• Experience with large language/image/video models

• Ability to work independently with light touch guidance and oversight

• Bachelor’s degree preferred.

• Client is seeking an Image & Video Model Red Teamer to join our Generative AI Media Safety team. Generative AI is a research to production organization focused on making significant progress in AI and being a bridge between AI research and client Platforms products. Individuals in this role are expected to be experienced in data annotation.

• The successful candidate will be responsible for interacting with our (Text/Image) -> (Image/Video) model expressly to identify potential weaknesses and vulnerabilities to improve accuracy while increasing trust and safety of the model.

  Responsibilities:

• Execute plans to test the safety of our Text -> Image model.

• Collaborate with the development team to design and execute probing text prompts, and provide feedback on the safety and quality of the image outputs and the probing methods

• Stay up-to-date on the latest techniques and tools to ensure the model remains secure.

  Story Behind the Need – Business Group & Key Projects:

• Generative AI Media Safety team

• Future contractors could be needed in the next 12-months depending on whether or not we scale the effort to other products research areas

• We require our human labelers to be able to see our internal taxonomy of risks as well as our sensitive, unrealized model output and user data. Given the rapid cycles of model refinement, it is preferable for a trained workforce of CW’s can complete red team tasks on an ongoing basis after an initial training.

  Compelling Story & Candidate Value Proposition:

• You will work on one of the most advanced pieces of technology in the world today

• Contribute to developing the latest generative AI products within the industry

• Unique opportunity to gain experience within the generative AI space

• Unique opportunity to contribute to making AI safe for people

  Typical Day in the Role:

• 8 hours per day

• Not expecting overtime, but in extreme cases it might be a possibility if breaking issues emerge

  How will performance be measured:

• Performance will be measured based on the number of attempts made by each CW to “break” the foundation model through an assigned prompt. We are expecting approximately 75 attempts per week will be made by each CW

• When we refer to attempts, we mean attempts to cause our models to output undesirable results, either because they violate explicit policies or else because they fail to meet the safety bar for our products and services.
  • **Only those lawfully authorized to work in the designated country associated with the position will be considered.**
  • **Please note that all Position start dates and duration are estimates and may be reduced or lengthened based upon a client’s business needs and requirements.**

Benefits:

For information and details on employment benefits offered with this position, please visit . Should you have any questions/concerns, please contact our HR Department via our secure .

California Pay Equity:

For information and details on pay equity laws in California, please visit the State of California Department of Industrial Relations' website .

Rose International is an Equal Opportunity Employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, age, sex, sexual orientation, gender (expression or identity), national origin, arrest and conviction records, disability, veteran status or any other characteristic protected by law. Positions located in San Francisco and Los Angeles, California will be administered in accordance with their respective Fair Chance Ordinances.

If you need assistance in completing this application, or during any phase of the application, interview, hiring, or employment process, whether due to a disability or otherwise, .

Rose International has an official agreement (ID #132522), effective June 30, 2008, with the U.S. Department of Homeland Security, U.S. Citizenship and Immigration Services, Employment Verification Program (E-Verify). (Posting required by OCGA 13/10-91.).

Job Tags

Similar Jobs