Salesforce - San Francisco, CA

posted 17 days ago

Full-time - Senior
San Francisco, CA
Publishing Industries

About the position

The Senior Technical AI Ethicist - AI Red Teamer role at Salesforce focuses on ensuring the ethical use of AI technologies. This position involves conducting adversarial testing to identify potential risks and vulnerabilities in AI models and products, collaborating with cross-functional teams to integrate ethical practices into the AI development lifecycle, and developing proactive measures to mitigate risks posed by malicious actors. The ideal candidate will have a strong technical background in AI ethics and experience in adversarial testing.

Responsibilities

  • Provide technical leadership in designing, prototyping, and implementing comprehensive adversarial testing strategies.
  • Mentor and guide collaborator teams on adversarial testing standard processes.
  • Collaborate with cross-functional teams to integrate adversarial testing frameworks into the AI development lifecycle.
  • Contribute to the development of detection models and safety guardrails to prevent risks from bad actors.
  • Research and implement innovative techniques for enhancing AI safety and robustness.
  • Write clean, efficient, and well-documented code primarily in Python to support research efforts.
  • Develop and maintain a repository of reusable code modules for adversarial testing processes.
  • Participate in scoping, documenting, and implementing tests with partner teams.
  • Test for technical vulnerabilities, model vulnerabilities, and harm/abuse including bias and toxicity.
  • Write reports covering the goals and outcomes of testing operations.

Requirements

  • A related technical degree required.
  • 5-7 years of proven experience in Software Engineering, AI ethics, AI research, or similar roles.
  • Experience creating heuristic-based detection logic for identifying anomalous activity.
  • Experience using SQL and relational databases.
  • Ability to use Python, R, or other scripting languages for data analysis at scale.
  • Experience in problem-solving and troubleshooting sophisticated issues.
  • Experience in analyzing large-scale data sets and communicating findings to diverse audiences.
  • Proven organizational and execution skills in a fast-paced environment.
  • Experience working in a technical environment with cross-functional teams.
  • Excellent written and oral communication skills.

Nice-to-haves

  • Experience with adversarial machine learning techniques.
  • Familiarity with socio-technical systems and responsible AI practices.

Benefits

  • Flexible work environment with remote options.
  • Opportunities for professional development and continuous learning.
© 2024 Teal Labs, Inc
Privacy PolicyTerms of Service