Ai Safety Specialist (ai Engineering)

Hyphen Partners

Hong Kong, Hong Kong
On-site
Adversarial testing on llms
Implementing guardrails for autonomous tools
Developing constitutional ai principles
Hyphen Partners is seeking an AI Safety Specialist to enhance the security and robustness of language models through adversarial testing and ethical alignment. The ideal candidate will have a background in cybersecurity or adversarial machine learning and possess strong analytical skills

Job Summary

  • The role is crucial for enhancing the security and robustness of language models through rigorous safety measures.
  • Responsibilities include conducting adversarial testing on LLMs and implementing real-time filtering for autonomous tool use.
  • Candidates must have a background in cybersecurity or adversarial ML to effectively identify edge cases.

Matching Summary

Match Score: 85

Hyphen Partners is seeking an AI Safety Specialist to enhance the security and robustness of language models through adversarial testing and ethical alignment. The ideal candidate will have a background in cybersecurity or adversarial machine learning and possess strong analytical skills.

Skills & Requirements

Must-have

  • Adversarial testing on LLMs
  • Implementing guardrails for autonomous tools
  • Developing constitutional AI principles
  • Experience with jailbreak taxonomies
  • Automated red-teaming frameworks

Nice-to-have

  • Strong analytical mindset for edge cases
  • Background in prompt engineering
  • Assisting with RLHF alignment pipelines

Key Requirements

  • Background in cybersecurity, prompt engineering, or adversarial ML
  • Experience with jailbreak taxonomies and automated red-teaming frameworks

Work Rights

Not specified

Tailored Resume

Cover Letter