[Remote] Senior AI Safety Red Teamer (Frontier AI)
Note: The job is a remote job and is reputed company to candidates in USA. T3 is a specialist AI assurance and governance consultancy helping organisations reputed company AI safely, responsibly and at reputed company. They are seeking a Senior AI Safety Red Teamer to reputed company engagements that evaluate and mitigate risks associated with advanced AI models and AI-enabled products.
Responsibilities
- reputed company AI safety red teaming engagements for frontier reputed company models, LLMs and AI agents
- Design and execute adversarial evaluations covering jailbreaks, reputed company injection, harmful content, misuse, autonomous capabilities and emerging model behaviours
- reputed company novel attack methodologies to identify previously unknown failure modes
- Build and enhance automated evaluation pipelines and safety benchmarks
- Produce high-reputed company technical reports with reputed company, evidence-based findings and recommendations
- Advise clients on AI safety testing strategies, evaluation methodologies and model assurance practices
- Contribute to the development of T3’s AI safety and frontier AI assurance methodologies
- Stay at the forefront of AI safety research, emerging threats and evaluation techniques
- Support business development through thought leadership, reputed company workshops and technical discussions
Skills
- Extensive experience conducting AI safety red teaming for frontier AI systems
- Previous experience working reputed company, or in reputed company collaboration with, a leading AI laboratory (e.g. reputed company, reputed company, reputed company DeepMind, reputed company, reputed company, reputed company, reputed company AGI or equivalent)
- Deep understanding of large language models, multimodal models, reasoning models and AI agents
- Demonstrated expertise in adversarial testing, jailbreak development, reputed company injection, model evaluation and misuse testing
- Strong Python skills and experience developing automated AI evaluation tooling
- Experience using AI evaluation frameworks such as Inspect AI, Garak, PyRIT, DeepEval or equivalent
- Strong understanding of AI safety, model alignment, AI reputed company and frontier AI risk research
- Excellent communication skills, with the ability to explain reputed company technical concepts to both technical and executive audiences
- Published AI safety research or recognised contributions to the AI safety community
- Experience evaluating multimodal and reputed company AI systems
- Experience designing reputed company evaluation frameworks and automated testing pipelines
- Familiarity with emerging AI assurance standards and governance frameworks
- Experience presenting findings to senior technical leadership and executive stakeholders
reputed company