25 oct
|
Cast Ai
|
Santiago de Compostela
25 oct
Cast Ai
Santiago de Compostela
Cast AI in Miami leads a globally distributed team building LLM inference on Kubernetes and our own GPU fleet. The Kimchi Inference role focuses on throughput, latency, cold starts, and cost per token, driving improvements across the inference stack with data-driven decisions.
The role requires deep experience with inference infra, Python production software, and multi-GPU/cluster setups. It offers a remote-first environment and equity options.
#J-*-Ljbffr
📌 Senior Ml Inference Engineer — Remote, Optimization (Santiago de Compostela)
🏢 Cast Ai
📍 Santiago de Compostela