2 months ago
Remote, EMEASenior
Responsibilities
- Lead inference strategy for EMEA AI-native customers from proof of concept through production-scale deployment.
- Identify and resolve inference bottlenecks involving latency, efficiency, cost per token, memory utilization, and low-latency networking.
- Architect and optimize high-performance inference pipelines using NVIDIA Dynamo, TensorRT-LLM, vLLM, SGLang, and other inference backends.
- Align NVIDIA and customer teams around strategic technology decisions and lead technical initiatives.
- Translate customer deployment insights into actionable feedback for the NVIDIA inference-stack roadmap.
Requirements
- MS or PhD in Computer Science, Engineering, or equivalent experience in the field.
- 8+ years of experience in AI/ML infrastructure, including deep expertise in LLM/VLM inference optimization and production deployment at scale.
- Deep understanding of transformer inference acceleration, including INT4/FP8 quantization, speculative decoding, disaggregated inference, continuous batching, KV cache optimization, and WideEP for MoE models.
- Understanding of GPU memory hierarchies and low-latency networking and their impact on inference performance.
- Proven ability to lead technical initiatives and communicate effectively with research scientists, infrastructure engineers, and executives.
- Preferred experience with NVIDIA’s inference stack, GPU orchestration on Kubernetes, frontier AI labs or hyperscale inference teams, and open-source projects such as vLLM, SGLang, KServe, or NVIDIA Dynamo.
Benefits
- Competitive salary and comprehensive benefits package.
- Base salary varies by location, experience, and comparable employee pay; the listed Poland ranges are 292,500 PLN–507,000 PLN for Level 4 and 375,000 PLN–650,000 PLN for Level 5.
Tech Stack
KubernetesNim
Categories
Solutions Engineering
About Nvidia
Nvidia designs and sells GPUs and accelerated computing platforms for data centers, AI/ML, graphics, gaming, and automotive, monetizing through hardware, software platforms (CUDA, AI frameworks), and systems like DGX and networking. Customers include cloud providers, enterprises, researchers, and OEMs. Founded in 1993 and headquartered in Santa Clara, it is a public company traded on NASDAQ under NVDA.