The Research Scientist candidate will use their skills in system design and modeling to advance AI safety and security research. These roles will require research and problem-solving skills to design, develop, and evaluate novel approaches to ensuring AI systems are safe, secure, and aligned with human values. These roles will work in a focused incubation team and collaborate with a large and wide-ranging set of scientists and engineers in the greater organization.

Responsibilities

Perform fundamental and applied research to advance the scientific and technological frontiers of AI safety and security
• Develop and evaluate methods for ensuring AI systems behave safely and as intended, including alignment techniques and robustness testing
• Investigate paradigms for detecting and mitigating adversarial attacks, model vulnerabilities, and potential misuse of AI systems
• Develop algorithms based on state-of-the-art machine learning and neural network methodologies with a focus on safety and security
• Define, build and benchmark new safety and security functionalities needed for the next generation of AI
• Conduct research towards long-term product goals while identifying intermediate milestones
• Plan and execute novel research based on long-term objectives of the organization

Minimum Qualifications
• Bachelor's degree in Computer Science, Computer Engineering, relevant technical field, or equivalent practical experience
• Currently has or is in the process of obtaining a PhD degree in the field of Artificial Intelligence, Machine Learning, Computer Security, a related field, or equivalent practical experience
• Experience with any of the following research areas: AI safety, AI alignment, adversarial machine learning, model robustness, AI security, red-teaming AI systems, interpretability, or trustworthy AI
• Experience in relevant AI safety and security research areas, such as: alignment techniques, reward modeling, RLHF, constitutional AI, jailbreak prevention, model robustness, or adversarial attack detection

Preferred Qualifications
• Experience working with large language models and evaluating their safety properties
• 2+ years of industry experience in relevant AI safety and security research areas
• Experience building systems based on machine learning and/or deep learning methods
• Proven track record of achieving significant results as demonstrated by grants, fellowships, patents, as well as publications at leading workshops, journals or conferences in Machine Learning (NeurIPS, ICML, ICLR), Security (IEEE S&P, USENIX Security, CCS), or AI Safety venues
• Experience with manipulating and analyzing complex, large scale, high-dimensionality data from varying sources
• Experience working and communicating cross-functionally in a team environment
• Demonstrated research and software engineering experience via an internship, work experience, coding competitions, or widely used contributions in open source repositories (e.g. GitHub)
• Experience with deep learning frameworks (such as PyTorch, Tensorflow) and Python
• Experience solving complex problems and comparing alternative solutions, tradeoffs, and different perspectives to determine a path forward