Ai Safety Specialist (ai Engineering)

Hyphen Partners

Boston, United States
On-site
Adversarial testing on llms
Implementing guardrails for ai
Jailbreak taxonomy experience
The role focuses on enhancing the security and robustness of language models through rigorous adversarial testing

Job Summary

  • The role focuses on enhancing the security and robustness of language models through rigorous adversarial testing.
  • Candidates will implement protective measures including guardrails and real-time filtering for autonomous tool use.
  • The position requires aligning AI behavior with ethical principles using constitutional AI and RLHF methodologies.

Matching Summary

The role focuses on enhancing the security and robustness of language models through rigorous adversarial testing.

Skills & Requirements

Must-have

  • Adversarial testing on LLMs
  • Implementing guardrails for AI
  • Jailbreak taxonomy experience
  • Automated red-teaming frameworks

Nice-to-have

  • Strong analytical mindset
  • Constitutional AI principles
  • RLHF alignment pipelines

Key Requirements

  • Background in cybersecurity or adversarial ML
  • Experience with prompt engineering
  • Analytical skills for edge cases

Work Rights

Not specified

Tailored Resume

Cover Letter