AI Safety Specialist (AI Engineering)
AustraliamidQuick Summary
Conduct adversarial testing on LLMs and multimodal agents. Implement guardrails and real-time filtering for autonomous tool use.
Background in cybersecurity, prompt engineering, or adversarial ML. Experience with jailbreak taxonomies and automated red-teaming frameworks. Strong analytical mindset for identifying edge cases.
We are searching for an AI Safety Specialist who will play a crucial role in enhancing the security and robustness of language models. You will ensure the safe deployment of AI systems by conducting adversarial testing, implementing protective measures, and aligning AI behavior with ethical principles.
Responsibilities
~1 min read- →Conduct adversarial testing on LLMs and multimodal agents.
- →Implement guardrails and real-time filtering for autonomous tool use.
- →Develop constitutional AI principles and assist with RLHF alignment pipelines.
Requirements
~1 min read- Background in cybersecurity, prompt engineering, or adversarial ML.
- Experience with jailbreak taxonomies and automated red-teaming frameworks.
- Strong analytical mindset for identifying edge cases.
Location & Eligibility
Listing Details
- Posted
- April 24, 2026
- First seen
- April 24, 2026
- Last seen
- May 4, 2026
Posting Health
- Days active
- 10
- Repost count
- 0
- Trust Level
- 35%
- Scored at
- May 5, 2026
Signal breakdown
Web3 and AI talent recruitment agency based in Hong Kong with 700+ placements globally
Please let Hyphenconnect know you found this job on Jobera.
4 other jobs at Hyphenconnect
View all →Explore open roles at Hyphenconnect.
Browse Similar Jobs
Stay ahead of the market
Get the latest job openings, salary trends, and hiring insights delivered to your inbox every week.
No spam. Unsubscribe at any time.
AI Safety Specialist (AI Engineering)