At Google DeepMind, the business problem is to identify, assess, and mitigate potential catastrophic risks from current and future AI systems, ensuring safety and ethics are the highest priority.
Requirements
- Extensive research experience with deep learning and/or foundation models
- Adept at generating ideas and designing experiments, and implementing these in Python with real AI systems
- Experience in areas such as frontier risk assessment and/or mitigations, safety, and alignment
- Engineering experience with LLM training and inference
- PhD in Computer Science or Machine Learning related field
- A track record of publications at venues such as NeurIPS, ICLR, ICML, RL/DL, EMNLP, AAAI and UAI
- Experience with collaborating or leading an applied research project
Responsibilities
- Identifying new risk pathways within current areas (loss of control, ML R&D, cyber, CBRN, harmful manipulation) or in new ones
- Conceiving of, designing, and developing new ways to measure pre-mitigation and post-mitigation risk
- Forecasting and scenario planning for future risks which are not yet material
- Designing, implementing, and empirically validating approaches to assessing and managing catastrophic risk from current and future frontier AI systems
- Building decision-relevant and trustworthy evaluation systems that prioritise compute and effort on risk measurements with the highest value of information
- Assessing the extent to which proposed and implemented mitigations actually cover the identified risks, and to measure how successfully they generalize to novel settings
- Rapidly familiarising yourself with internal and external codebases
Other
- Strong, clear communication skills, confident engaging technical stakeholders to share research insights tailored to their background
- Ability to work with strong contributors to make progress towards a shared ambitious goal
- Diversity of experience, knowledge, backgrounds and perspectives
- Commitment to equal employment opportunity regardless of sex, race, religion or belief, ethnic or national origin, disability, age, citizenship, marital, domestic or civil partnership status, sexual orientation, gender identity, pregnancy, or related condition
- Ability to adapt to pragmatic constraints around compute and researcher time that require us to prioritise effort based on the value of information
