Perform adversarial testing and red-teaming on large language and multimodal models, implement runtime guardrails and filtering, and help develop constitutional AI principles and RLHF alignment pipelines to ensure safe AI deployment.
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:
- 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.
Qualifications:
- Background in cybersecurity, prompt engineering, or adversarial ML.
- Experience with jailbreak taxonomies and automated red-teaming frameworks.
- Strong analytical mindset for identifying edge cases.
Similar Jobs
Events • Food • Travel • Hospitality • Hotels & Resorts
Provide beauty therapy and massage treatments while delivering personalized, high-quality guest experiences. Maintain professional relationships with spa leadership and colleagues, uphold integrity and presentation standards, and contribute to individual and team retail targets. The role includes training and career development opportunities within Hilton.
Aerospace • Information Technology • Software • Cybersecurity • Design • Defense • Manufacturing
Performs warehouse, inventory management, priority demand, receipt, storage, packaging, shipping, and distribution activities supporting Boeing’s C-17 Globemaster fleet. Uses U.S. and Defence inventory systems, manages serviceable and non-serviceable inventory accounts, supports aircraft demands and international fleet partners, and processes exports. Requires shift and on-call work, with forklift experience preferred. The role is based at RAAF Base Amberley and requires Australian citizenship.
Top Skills:
Defence ErpGold EspMS OfficeWarehouse On Web
Cloud • Information Technology • Productivity • Security • Software • App development • Automation
Design, build, deploy, and operate evaluation and optimization systems for Rovo AI agents. Develop offline benchmarks, online quality metrics, model-based judges, and production monitoring. Use evaluation results to improve prompts, retrieval, tool use, routing, quality, cost, and latency. Lead projects from problem definition through delivery, contribute to technical reviews, coach engineers, and communicate ML trade-offs to stakeholders.
Top Skills:
Cloud Data EnvironmentsDistributed Data ProcessingKotlinLarge Language Models (Llms)PythonRetrieval-Augmented Generation (Rag)SQL
What you need to know about the Melbourne Tech Scene
Home to 650 biotech companies, 10 major research institutes and nine universities, Melbourne is among one of the top cities for biotech. In fact, some of the greatest medical advancements were conceptualized and developed here, including Symex Lab's "lab-on-a-chip" solution that monitors hormones to predict ovulation for conception, and Denteric's vaccine for periodontal gum disease. Yet, the thousands of people working in the city's healthtech sector are just getting started, to say nothing of the tech advancements across all other sectors.
