> Markdown version of [/jobs/ext/3696006-solutions-architect-ai-inference](https://www.wearedevelopers.com/jobs/ext/3696006-solutions-architect-ai-inference). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Solutions Architect, AI Inference

- **Company:** NVIDIA Ltd.
- **Location:** Santa Clara, CA, United States
- **Experience:** Expert
- **Salary:** $184,000.0 - $287,500.0
- **Contract:** Permanent contract
- **Skills:** Artificial Intelligence, Automated Storage and Retrieval Systems, DevOps, Distributed Systems, Open Source Technology, Design of Telemetry/logging Agents, Large Language Models, Discretization, Kubernetes, SGLang, Triton Inference Server, TensorRT, VLLM, Model Inference
- **Published:** October 12, 2026
- **Apply:** https://www.juju.com/job/1_ScrapingHub33470-JR2023533

## About the Role

What we need to see: + 6+ Years in Solutions Architecture (or Solution Engineering, Forward-Deployed Engineering, or similar) driving customer engagements to deploy distributed systems, including 2+ years with AI workloads on Kubernetes. + Experience with one of NVIDIA Dynamo, Triton Inference Server, or TensorRT-LLM for model optimization and serving. + Deep knowledge of modern inference best practices including disaggregated serving, multi-tier KV cache management, speculative decoding, quantization and custom inference kernels. + Hands-on full-stack agent design with modern sandboxing, memory and retrieval systems with evaluation, skill design and governance. + BS in CS/Engineering or equivalent experience.
Ways to stand out from the crowd: + Prior experience deploying NVIDIA inference technologies such as Dynamo, NIXL and Grove. + Experience with model customization techniques such as SFT, DPO, GRPO, RLVR and corresponding data curation techniques. + Contributions to open-source projects relevant to the above.

## Description

What you'll be doing: + Work with inference partners who build cutting-edge inference services, teach them the value of our stack and bring back product insights that benefit the whole industry. + Build and operate inference recipes with tools like NVIDIA Dynamo, distributing tasks among GPU workers to improve efficiency. + Accelerate inference pipelines using TensorRT-LLM, vLLM, SGLang, and other backends to ensure seamless integration with disaggregated inference. + Evangelize devops best-practices for such as managing kubernetes clusters, configuring compute fabrics, and observability. + Provide mentorship and technical leadership to customers and internal teams, guiding them through the deployment of disaggregated inference systems and resolving complex issues.