Senior Solutions Architect - Large Scale AI Inference

Stack

Responsibilities

• ▹Guide EMEA customers in deploying and optimizing large-scale inference workloads on multi-node GPU clusters
• ▹Architect efficient inference pipelines for dense and sparse/latent MoE models distributing workload among thousands of GPUs
• ▹Improve inference efficiency via quantization (INT4/FP8), speculative decoding, disaggregated prefill/decode, KV cache management and WideEP
• ▹Collaborate with NVIDIA product teams (Dynamo, TensorRT-LLM, NIXL) to accelerate customer success
• ▹Build the AI inference developer community across EMEA through workshops, hackathons and reference architectures

Requirements

• ▹MS or PhD in Computer Science, Engineering, High-Performance Computing, or equivalent professional experience
• ▹5+ years of experience in neural network inference optimization
• ▹Solid understanding of transformer inference optimization: quantization, disaggregated inference, speculative decoding, continuous batching, KV cache optimization
• ▹Practical experience in MoE inference at scale: expert parallelism, WideEP, all-to-all communication, routing overhead, load balancing
• ▹Ability to engage at a deep technical level with ML engineers, researchers and systems architects

Nice to have

• ▹Hands-on experience with NVIDIA Dynamo, NIXL, Grove or emerging disaggregated inference tooling
• ▹Understanding of GPU memory hierarchies and high-speed interconnects (NVLink, InfiniBand, RDMA, UCX)
• ▹Contributions at advanced AI labs or large-scale AI infrastructure providers running inference on thousands of GPUs
• ▹Published work or benchmarks in large-scale AI inference

Soft skills

What we offer

• ▹Highly competitive salary and comprehensive benefits package
• ▹For Poland the base salary range is 292,500 - 507,000 PLN

About the company

NVIDIA is widely considered one of the technology world's most desirable employers and is committed to a diverse work environment.