Todas as vagas
Senior ML Engineer | Kimchi (Inference Stack Optimization)
Kimchi
Holanda · Aceita remotoSênior (5–10 anos)Tempo integralPublicada há 15 dias
Sobre a vaga
O que você vai fazer
You will be responsible for optimizing the inference stack to improve throughput, latency, and cost-efficiency. This includes tuning loaders, schedulers, and kernels while managing distributed inference topologies and KV cache performance.
O que eles procuram
You must have 5+ years of experience building real ML systems with deep expertise in inference or training infrastructure. Proficiency in Python and hands-on experience with engines like vLLM, SGLang, or TensorRT-LLM is required.
Descrição completa