Senior AI Researcher - Remote/Hybrid, LLM & Optimization

V2EX in Sydney-based startup seeks a Senior AI Researcher to lead KV cache optimization, CUDA and LLM inference acceleration, with hybrid work and relocation to Sydney. The role targets high-performance inference, model compression, and research-to-production delivery.

The candidate will design optimized inference pipelines, evaluate models, mentor engineers, and drive production-ready research. English interviews, relocation support, and ESOP are offered.