SpotAI

The Secure, Private, Open and Trustworthy (SPOT) AI lab at MBZUAI, led by Nils Lukas. We work on secure and private machine learning and AI safety — including content watermarking, privacy-preserving inference, AI safety & security, and conversational agents with social intelligence.

We are hiring multiple postdocs on two new external grants: [Multi-Agent Privacy] — multi-agent systems with privacy for healthcare, with Praneeth Vepakomma and Preslav Nakov. [AI Safety Advisory] — AI safety for smallholder advisory, with Salem Lahlou and Martin Takáč. You should have strong first-author papers at top venues (NeurIPS, ICML, ICLR, IEEE S&P, CCS, USENIX Security) in multi-agent systems, self-improvement, AI safety or (differential) privacy — work like our ICLR'26 DP-Fusion. You get dedicated NVIDIA H200s and a highly competitive package. To apply, e-mail me a short technical note on a favourite paper of your own and why it interests you, using the tag above as your subject prefix: nils.lukas@mbzuai.ac.ae.