# Architect - LLM Inference at Scale

**Company**: NVIDIA
**Experience**: senior
**Job type**: full-time
**Category**: Engineering
**Industry**: Technology

**Apply**: https://nvidia.wd5.myworkdayjobs.com/en-US/NVIDIAExternalCareerSite/job/Israel-Yokneam/Senior-Software-Architect--AI-Networking_JR2025070?utm_source=yubhub.co&utm_medium=jobs_feed&utm_campaign=apply
**Canonical**: https://yubhub.co/jobs/job_af748ef2-f0b

## Description

NVIDIA is seeking an Architect to help shape the future of LLM inference at scale. You will work across software and hardware domains to design and optimize inference infrastructure for large language models running on sophisticated GPU clusters.

**Responsibilities:**

- Design and evolve scalable architectures for multi-node LLM inference across GPU clusters.

- Develop infrastructure to optimize latency, throughput, and cost-efficiency of serving large models in production.

- Collaborate with model, systems, compiler, and networking teams to ensure complete, high-performance solutions.

- Prototype novel approaches to KV cache handling, tensor/pipeline parallel execution, and dynamic batching.

- Evaluate and integrate new software and hardware technologies relevant to Core Spectrum-X technologies.

- Work closely with internal teams and external partners to translate high-level architecture into reliable, high-performance systems.

- Author design documents, internal specs, and technical blog posts and contribute to open-source efforts when appropriate.

**Requirements:**

- Bachelor’s, Master’s, or PhD in Computer Science, Electrical Engineering, or equivalent experience.

- 8+ years of experience building large-scale distributed systems or performance-critical software.

- Deep understanding of deep learning systems, GPU acceleration, and AI model execution flows and/or high performance networking.

- Proven software engineering skills in C++ and/or Python, preferably demonstrate strong familiarity with CUDA or similar platforms.

- Strong system-level thinking across memory, networking, scheduling, and compute orchestration.

- Excellent communication skills and ability to collaborate across diverse technical domains.

**Preferred Qualifications:**

- Experience working on LLM - training or inference pipelines, transformer model optimization, or model-parallel deployments.

- Proven success in profiling and optimizing performance bottlenecks across the LLM training or inference stack.

- AI Accelerators and distributed communication patterns, congestion control and/or load balancing.

- Shown optimization process for complex systems, deployed at scale to make impact.

- Proven experience successfully driving complex organizational processes from planning through implementation.

NVIDIA offers highly competitive salaries and a comprehensive benefits package.

## Skills

### Required
- C++
- Python
- CUDA
- GPU acceleration
- deep learning systems
- high performance networking

### Nice to have
- LLM inference
- transformer model optimization
- model-parallel deployments
- AI Accelerators
- distributed communication patterns
- congestion control
- load balancing

---

Source: [Apply at nvidia.wd5.myworkdayjobs.com](https://nvidia.wd5.myworkdayjobs.com/en-US/NVIDIAExternalCareerSite/job/Israel-Yokneam/Senior-Software-Architect--AI-Networking_JR2025070?utm_source=yubhub.co&utm_medium=jobs_feed&utm_campaign=apply)