Hyphen Connect is seeking an AI Safety Specialist to strengthen the robustness and safety of language models in Gladstone, Australia. You will conduct adversarial testing on LLMs and multimodal agents, aiming to improve reliability and ethical behavior.
Responsibilities include implementing guardrails for autonomous tool use and developing constitutional AI principles, contributing to RLHF alignment pipelines and real-time safety controls.
J-18808-Ljbffr
📌 Ai Safety Engineer: Adversarial Testing & Alignment Gladstone (Gladstone Central)
🏢 Hyphen Connect
📍 Gladstone Central
Reply to this offer
Impress this employer describing Your skills and abilities, fill out the form below and leave Your personal touch in the presentation letter.