Groq, Inc. is seeking a seasoned engineer to optimize an inference serving software stack for high-throughput, low-latency delivery of tokens from large models.
You will work across model internals, runtime software, and supporting GPU/accelerator hardware to push performance in production. The role requires 5+ years shipping performance-critical products, strong transformer expertise, and fluency in at least one systems language plus a high-level language.
#J-18808-LjbffrSenior Inference Engineer for High-Throughput LLM Serving in tx at Unknown Company
This position is listed as full time and onsite.