Senior AI Inference Architect & Dynamo Tech Lead

NVIDIA; Texas; On-site; USD 320,000 - 489,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA seeks a Distinguished Engineer to join the Dynamo team, leading AI inference initiatives and shaping technology directions across NVIDIA platforms. This role requires deep technical guidance and impact on next-generation inference on NVIDIA hardware.

You will contribute to Dynamo open source projects, collaborate with storage, networking, hardware and performance teams, and represent Dynamo with customers and the AI community.

Qualifications

• 18+ years of proven experience in systems software engineering.
• Expertise in AI inference space, such as operating production inference systems at scale.
• Experience serving as a senior technical leader with influence.
• Proficiency in Rust, Python, and Go and familiarity with cloud platforms (AWS, GCP, Azure).

Responsibilities

• Contribute to the Dynamo family of open source projects.
• Serve as a technical expert in AI inferencing and push the frontier of what's possible.
• Represent Dynamo and NVIDIA with customers, partners and the AI community.
• Lead critical initiatives around resiliency, performance and scalability for Dynamo and AI inference.
• Build and drive Dynamo to be a production-ready, data center-scale AI inferencing platform.
• Collaborate with diverse partner teams at NVIDIA across storage, networking, hardware and performance.
• Keep abreast of the latest advancements in AI/ML infrastructure technologies and promote their implementation.

Skills

Rust

Python

Go

Leadership in tech teams

Cloud platforms (AWS/GCP/Azure)

Problem-solving

Communication

Education

BS/MS/PhD in CS/CE/AI

Job description

NVIDIA seeks a Distinguished Engineer to join the Dynamo team, leading AI inference initiatives and shaping technology directions across NVIDIA platforms. This role requires deep technical guidance and impact on next-generation inference on NVIDIA hardware.

You will contribute to Dynamo open source projects, collaborate with storage, networking, hardware and performance teams, and represent Dynamo with customers and the AI community.