Senior AI Inference Systems Engineer

NVIDIA Corporation; Santa Clara (CA); Hybrid; USD 224,000 - 431,250; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA Corporation in Santa Clara (hybrid) is seeking a Senior System Software Engineer to join a fast-moving team developing the Dynamo AI inference platform. You will contribute to GPU-accelerated open source software powering next-gen AI models.

The role emphasizes building robust, high-performance components for disaggregated inference, collaborating with cross-functional teams, and advancing inference engines like vLLM, SGLang, and TensorRT-LLM to enable tool calls and long-horizon

Qualifications

• Masters or PhD or equivalent experience required.
• 10+ years in computer science, computer engineering, or related field.
• Excellent Rust and Python programming, debugging and performance analysis skills.
• Understanding modern LLM API semantics, tool calling, and session semantics.

Responsibilities

• Develop open source software to serve inference of trained AI models on GPUs.
• Advance Dynamo's disaggregated inference frontend across vLLM, SGLang, and TensorRT-LLM.
• Balance throughput and latency while managing resources for multi-model workloads.
• Collaborate with team leads to prioritize features and write tests.

Skills

Rust programming

Python programming

Software design

Performance analysis

LLM API semantics

Open-source contributions

Education

Master's or PhD in CS/CE or equivalent

Tools

vLLM

TensorRT-LLM

SGLang

Job description

NVIDIA Corporation in Santa Clara (hybrid) is seeking a Senior System Software Engineer to join a fast-moving team developing the Dynamo AI inference platform. You will contribute to GPU-accelerated open source software powering next-gen AI models.

The role emphasizes building robust, high-performance components for disaggregated inference, collaborating with cross-functional teams, and advancing inference engines like vLLM, SGLang, and TensorRT-LLM to enable tool calls and long-horizon