Specialised AI Engineer
This role involves designing and optimizing large-scale AI systems for training, post-training, and low-latency inference within a vertically integrated GenAI cloud platform. The engineer will tackle hard systems problems across distributed infrastructure, focusing on performance, efficiency, and developer experience. Work spans KV cache management, quantisation, fine-tuning, alignment, evaluation, and scalable APIs for internal and external AI engineering teams.
NScale
London, United Kingdom
On-site
Permanent