Associate AI Researcher, F5

• Advanced degree (Master's or PhD) in Computer Science, Artificial Intelligence, Machine Learning, Cybersecurity, Statistics, Mathematics, or a closely related quantitative field. (Alternatively, a Bachelor's degree in a relevant field with 1-2+ years of direct, demonstrable research experience in AI/ML)
• Solid understanding of machine learning, deep learning, and natural language processing concepts, with specific knowledge related to transformer architectures and LLMs
• Proficiency in Python programming
• Hands-on experience with common ML/DL frameworks (e.g., PyTorch, TensorFlow, JAX) and libraries (e.g., Hugging Face Transformers, scikit-learn)
• Demonstrated ability to conduct research, evidenced through academic projects, thesis work, publications, or relevant work experience
• Strong analytical, problem-solving, and critical thinking skills
• Excellent communication skills, capable of articulating complex technical concepts effectively
• A strong interest and motivation in AI safety, security, and ethical AI development
• Authorization to work in Ireland

Desirable

• We are seeking a motivated and technically skilled Junior or Associate AI Researcher to join our expanding AI Security research team in Dublin
• This position is aimed at individuals in the early stages of their research careers who are passionate about the critical intersection of Artificial Intelligence and Security
• You will actively contribute to the core mission of CalypsoAI by researching novel attack vectors against AI systems, particularly LLMs and emerging agentic systems, directly enhancing our platform's red-teaming capabilities
• Concurrently, you will research and develop innovative defense mechanisms and mitigation strategies that will be integrated into our AI security platform solutions
• Working collaboratively within a team of experts, your research will directly influence the products that help secure AI worldwide
• Conduct research into known and emerging vulnerabilities specific to LLMs, agentic AI systems, and other machine learning models (e.g., prompt injection, jailbreaking, data poisoning, adversarial attacks, privacy leaks, agent manipulation)
• Design, implement, and execute experiments to rigorously test the susceptibility of various AI models and systems to different attack vectors
• Develop proof-of-concept attacks and defenses, with a particular focus on those relevant to agentic AI systems
• Contribute to the development and implementation of novel methods and tools for detecting and mitigating vulnerabilities, feeding directly into CalypsoAI's platform
• Analyze the root causes of identified vulnerabilities and collaborate on devising and evaluating robust defense mechanisms
• Contribute research findings and developed techniques directly to the feature roadmap and capabilities of CalypsoAI's security platform
• Stay current with the latest academic research and industry trends in AI security, adversarial machine learning, trustworthy AI, and agentic systems
• Collaborate effectively with senior researchers, engineers, and product teams to integrate security research into actionable platform features
• Document research findings, experimental results, proposed solutions, and developed tools clearly and thoroughly
• Prepare and present findings to internal teams and potentially contribute to external publications or conference presentations