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
.png)
Greentech • Hardware • Internet of Things • Machine Learning • Software • Business Intelligence • Agriculture
Drive sales growth and customer success across a designated territory in the beef industry. Prospect, close deals, manage onboarding, maintain accounts, gather field feedback, and collaborate with Product and Support to improve Halter's virtual fencing solutions.
Artificial Intelligence • Fintech • Payments • Business Intelligence • Financial Services • Generative AI
Generate and qualify leads for the ANZ SME & Growth sales pipeline. Conduct outreach (email, calling), qualify prospects, arrange meetings for AEs, maintain CRM data, support reporting, and collaborate with marketing and cross-functional teams to improve targeting and handoffs.
Top Skills:
CRM
Artificial Intelligence • Fintech • Payments • Business Intelligence • Financial Services • Generative AI
Lead the design team, ensuring alignment with business objectives and fostering innovation. Oversee design initiatives, mentor designers, and advocate for user needs in product development.
Top Skills:
Information ArchitectureInteraction DesignUser TestingUx Methodologies
What you need to know about the Sydney Tech Scene
From opera to comedy shows, the Sydney Opera House hosts more than 1,600 performances a year, yet its entertainment sector isn't the only one taking center stage. The city's tech sector has earned a reputation as one of the fastest-growing in the region. More specifically, its IT sector stands out as the country's third-largest, growing at twice the rate of overall employment in the past decade as businesses continue to digitize their operations to stay competitive.
