Ai Safety Specialist (ai Engineering)

Hyphen Connect

San Francisco Bay Area, United States
On-site
Adversarial testing on llms
Implement guardrails for autonomous tools
Experience with jailbreak taxonomies
Hyphen Connect is seeking an AI Safety Specialist to enhance the security and robustness of language models through adversarial testing and the implementation of protective measures. The ideal candidate will have a background in cybersecurity or adversarial machine learning and a strong analytical mindset

Job Summary

  • The role focuses on enhancing the security and robustness of language models through rigorous adversarial testing.
  • Candidates will implement protective measures including real-time filtering for autonomous tool use to ensure safe deployment.
  • The position requires developing ethical alignment principles and assisting with RLHF pipelines to align AI behavior.

Matching Summary

Match Score: 85

Hyphen Connect is seeking an AI Safety Specialist to enhance the security and robustness of language models through adversarial testing and the implementation of protective measures. The ideal candidate will have a background in cybersecurity or adversarial machine learning and a strong analytical mindset.

Skills & Requirements

Must-have

  • Adversarial testing on LLMs
  • Implement guardrails for autonomous tools
  • Experience with jailbreak taxonomies
  • Automated red-teaming frameworks

Nice-to-have

  • Strong analytical mindset for edge cases
  • Background in prompt engineering
  • Constitutional AI principles development

Key Requirements

  • Background in cybersecurity or adversarial ML
  • Experience with automated red-teaming frameworks
  • Analytical mindset for identifying edge cases

Work Rights

Not specified

Tailored Resume

Cover Letter