Senior Solutions Architect – Large Scale AI Inference

NVIDIA Corporation; United States; Sur place; USD 75 000 - 130 000; Plein temps

Résumé du poste

NVIDIA is seeking a Senior Solutions Architect to lead large-scale production AI inference initiatives across the EMEA region, collaborating with customers and NVIDIA teams to optimize multi-node GPU deployments.

You will design efficient inference pipelines for dense and sparse MoE models, implement optimizations in quantization and KV cache, and improve performance and reliability.

Qualifications

• MS or PhD in Computer Science, Engineering, High-Performance Computing, or equivalent professional experience.
• 5+ years in Neural Networks inference optimization.
• Deep knowledge of transformers inference optimization (quantization, disaggregated inference, speculative decoding, continuous batching, KV cache).
• Experience with MoE inference at scale (expert parallelism, WideEP, all-to-all, routing overhead).
• Ability to engage with ML engineers, researchers, and systems architects.

Responsabilités

• Guide EMEA customers in deploying and optimizing large-scale inference workloads on multi-node GPU clusters.
• Architect efficient inference pipelines for dense and sparse MoE models distributing workload among thousands of GPUs.
• Improve inference efficiency across quantization, speculative decoding, disaggregated prefill/decode, KV cache management, and WideEP for large MoE deployments.
• Collaborate with NVIDIA product teams to accelerate customer success.
• Animate the AI inference developer’s community across EMEA through technical workshops, hackathons, and reference architectures.

Connaissances

MoE inference

Transformers optimization

NN inference

NVLink/InfiniBand

Stakeholder engagement

Formation

MS/PhD in CS/CE/HPC

Outils

CUDA

DGX systems

Description du poste

Location: France

We are looking for a Senior Solutions Architect with deep experience in large-scale production AI inference. You will collaborate with top EMEA AI Natives, AI infrastructure providers, and enterprises deploying AI at scale. As a trusted technical leader, you will ensure NVIDIA's inference stack achieves best performance, efficiency, and reliability. You will address the industry's toughest AI inference challenges at the intersection of AI and high-performance computing, driving innovations in areas such as multi-node Mixture-of-Experts (MoE) serving, interconnect-aware scheduling, memory-bound workload optimization, and next-generation inference architectures. Your work will establish the technical direction for scalable, high-performance AI inference across the most demanding production environments.

What you will be doing:

• Guide EMEA AI Natives 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 across quantization (INT4/FP8), speculative decoding, disaggregated prefill/decode, KV cache management, and WideEP for large MoE deployments.

• Collaborate with NVIDIA product teams (Dynamo, TensorRT-LLM, NIXL) to accelerate customer success.

• Animate the AI inference developer’s community across EMEA through technical workshops, hackathons, and reference architectures.

What we need to see

• MS or PhD in Computer Science, Engineering, High-Performance Computing, or equivalent professional experience.

• 5+ years of experience in Neural Networks inference optimization.

• Solid understanding of transformers 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, and load balancing at scale.

• Ability to engage effectively with ML engineers, researchers, and systems architects at a deep technical level.

Ways to stand out from the crowd

• 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).

• You have contributed to advanced AI lab or large scale AI infrastructure providers performing inference on thousands of GPUs.

• Published work or benchmarks in large-scale AI inference.

Widely considered to be one of the technology world’s most desirable employers, NVIDIA offers highly competitive salaries and a comprehensive benefits package. As you plan your future, see what we can offer

NVIDIA is committed to fostering a diverse work environment and proud to be an equal opportunity employer. As we highly value diversity in our current and future employees, we do not discriminate (including in our hiring and promotion practices) on the basis of race, religion, color, national origin, gender, gender expression, sexual orientation, age, marital status, veteran status, disability status or any other characteristic protected by law.

Your base salary will be determined based on your location, experience, and the pay of employees in similar positions. For Poland: The base salary range is 292,500 PLN - 507,000 PLN.