Job Description
- Lead initiatives to implement next-generation safety mitigations. Guide engineering and research teams in building the technical solutions, from fine-tuning techniques to classifier-based guardrails.
- Partner with Engineering, Product, Policy and Legal to set precedents and create defensible principles for new AI capabilities.
- Analyse the evolving AI threat landscape. Identify and forecast future misuse vectors and adversarial techniques, translating these insights into a proactive mitigation agenda.
- Become the go-to person for issues related to the area of the business and use the domain knowledge to provide partners with insights and analyses.
- Review and be exposed to sensitive or violative content as part of the role. Perform on-call responsibilities on a rotating basis, including weekend coverage/holidays.
