10 days ago
Base Salary
$184k - $357k/yr
Responsibilities
- Work with strategic inference partners to deploy distributed systems, communicate the value of NVIDIA’s stack, and provide product insights.
- Build and operate inference recipes that distribute tasks across GPU workers for improved efficiency.
- Optimize inference pipelines using TensorRT-LLM, vLLM, SGLang, and other backends for disaggregated inference.
- Advocate DevOps practices involving Kubernetes clusters, compute fabrics, and observability.
- Mentor customers and internal teams, provide technical leadership, and resolve complex deployment issues.
- Create reference architectures and guide partners and industry stakeholders on large-scale inference systems.
Requirements
- 6+ years of experience in Solutions Architecture, Solution Engineering, Forward-Deployed Engineering, or a similar customer-engagement role deploying distributed systems.
- At least 2 years of experience working with AI workloads on Kubernetes.
- Experience with NVIDIA Dynamo, Triton Inference Server, or TensorRT-LLM for model optimization and serving.
- Deep knowledge of disaggregated serving, multi-tier KV cache management, speculative decoding, quantization, and custom inference kernels.
- Hands-on experience designing agents with sandboxing, memory and retrieval systems, evaluation, skill design, and governance.
- BS in Computer Science or Engineering, or equivalent experience.
- Preferred qualifications include experience with NVIDIA Dynamo, NIXL, Grove, model customization methods such as SFT, DPO, GRPO, and RLVR, related data curation, and relevant open-source contributions.
Benefits
- Competitive salary, equity, and a comprehensive benefits package for employees and their families.
- Applications are expected to remain open at least until November 3, 2026.
Tech Stack
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.