Ai Safety Specialist (ai Engineering)

Hyphen Connect

Seattle, United States
On-site
Adversarial testing on llms
Implement guardrails for tool use
Constitutional ai principles development
The role is crucial for enhancing the security and robustness of language models through rigorous safety measures

Job Summary

  • The role is crucial for enhancing the security and robustness of language models through rigorous safety measures.
  • Candidates will conduct adversarial testing on LLMs and multimodal agents to ensure safe deployment.
  • Responsibilities include implementing protective measures and aligning AI behavior with ethical principles via RLHF pipelines.

Matching Summary

The role is crucial for enhancing the security and robustness of language models through rigorous safety measures.

Skills & Requirements

Must-have

  • Adversarial testing on LLMs
  • Implement guardrails for tool use
  • Constitutional AI principles development
  • Jailbreak taxonomies knowledge
  • Automated red-teaming frameworks

Nice-to-have

  • Strong analytical mindset
  • Identifying edge cases
  • Ethical alignment expertise

Key Requirements

  • Background in cybersecurity or adversarial ML
  • Experience with prompt engineering
  • Expertise in jailbreak taxonomies

Work Rights

Not specified

Tailored Resume

Cover Letter