AI Solutions Architect — Generative AI & LLM Inference

NVIDIA; Massachusetts; On-site; USD 184,000 - 288,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA is seeking outstanding AI Solutions Architects to help customers build solutions with our AI technology. You will work across teams, advising on inference for Generative AI and LLMs, and collaborate on performance analysis of inference software.

You will engage developers, researchers, and data scientists, travel up to 20%, and influence deployments using Kubernetes and MIG, with equity and benefits eligible.

Qualifications

• 8+ years of hands-on experience with Deep Learning frameworks such as PyTorch and TensorFlow.
• Strong fundamentals in programming, optimizations, and software design, especially in Python.
• Experience with GPU orchestration and MIG management within Kubernetes environments.
• Experience with containerization and orchestration, monitoring, and observability solutions for AI deployments.
• Excellent knowledge of the theory and practice of LLM and DL inference.
• Excellent presentation, communication and collaboration skills.

Responsibilities

• Partner with other solution architects, engineering, product and business teams. Understanding their strategies and technical needs and helping define high‑value solutions
• Dynamically engaging with developers, scientific researchers, and data scientists, gaining experience across a range of technical areas
• Strategically partnering with lighthouse customers and industry‑specific solution partners targeting our computing platform
• Working closely with customers to help them adopt and build creative solutions using NVIDIA technology and MLOps solutions
• Analyzing performance and power efficiency of AI inference workloads on Kubernetes
• Some travel to conferences and customers may be required (20%)

Skills

Deep Learning Expertise

Python Programming

GPU Orchestration

Kubernetes

LLM Inference

Presentation & Collaboration

Education

BS/MS/PhD in Computer Science or related field

Tools

NVIDIA NIM

Dynamo

TensorRT

TensorRT-LLM

Job description

NVIDIA is seeking outstanding AI Solutions Architects to help customers build solutions with our AI technology. You will work across teams, advising on inference for Generative AI and LLMs, and collaborate on performance analysis of inference software.

You will engage developers, researchers, and data scientists, travel up to 20%, and influence deployments using Kubernetes and MIG, with equity and benefits eligible.