Senior Inference Serving Engineer - High-Performance LLM Ops

Groq, Inc. is seeking a seasoned engineer to optimize an inference serving stack, moving models from training to high-throughput production delivery.

You will work on runtime software, GPU/accelerator integration, and model internals to achieve fast, reliable token delivery. The role requires 5+ years shipping performance-critical products and a deep understanding of transformer architectures, with fluency in at least one systems language and one high-level language.