Senior Solutions Architect – Large Scale Neural Networks Inference

This is a fully remote position, open to applicants in France, +4 more countries.

📋 Description

• Spearhead the inference strategy for a portfolio of EMEA AI Natives customers, overseeing engagements from the initial proof of concept through to production-scale implementations.

• Recognize inference challenges within customer deployments, including latency, efficiency, cost per token, memory usage, and low-latency networking.

• Design and enhance high-performance inference pipelines utilizing NVIDIA Dynamo, TensorRT-LLM, vLLM, SGLang, and other inference backends.

• Enhance GPU utilization and improve the efficiency of AI clusters.

• Convert customer insights and deployment trends into actionable product feedback.

• Formulate the development roadmap for the NVIDIA stack, encompassing Dynamo, TensorRT-LLM, and NIM.

• Establish the technical direction for AI inference throughout the EMEA region.

• Coordinate between NVIDIA and customer organization stakeholders to shape strategic technology decisions for next-generation AI inference at scale.

⛳️ Requirements

• MS or PhD in Computer Science, Engineering, or equivalent experience in the domain.

• Over 8 years of experience in AI/ML infrastructure, with substantial expertise in LLM/VLM inference optimization and large-scale production deployment.

• In-depth knowledge of transformer inference acceleration techniques, including quantization (INT4/FP8), speculative decoding, disaggregated inference, continuous batching, KV cache optimization, and WideEP for MoE models.

• Familiarity with GPU memory hierarchies and low-latency networking and their impact on inference performance.

• Demonstrated ability to lead technical initiatives successfully.

• Strong communication skills, adept at engaging with research scientists, infrastructure engineers, and executive team members.

• Experience with NVIDIA's inference stack, including TensorRT-LLM, Triton Inference Server, NIM, and NVIDIA Dynamo.

• Proficient in GPU orchestration on Kubernetes.

• Experience managing inference at scale within a leading AI lab or a hyperscale inference team.

• Contributions to open-source inference projects such as vLLM, SGLang, KServe, or NVIDIA Dynamo.

🏝️ Benefits

• Highly competitive salaries.

• Comprehensive benefits package.