Senior Gen AI Inference Engineer (Equity Eligible)

NVIDIA Corporation; Washington; Hybrid; USD 192,000 - 357,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA Corporation is seeking a Senior Research Engineer with a passion for Generative AI inference. You will help shape how AI is infused into products by developing optimized inferencing technologies and collaborating across research, engineering, and open-source communities.

Ideal candidates have 8+ years in deep learning frameworks (PyTorch or TensorFlow), strong CS fundamentals, and experience evaluating LLMs or agentic benchmarks.

Qualifications

• Bachelor's or Master's in CS or equivalent experience.
• 8+ years in DL frameworks (PyTorch or TensorFlow).
• Experience designing or running LLM evaluations/benchmarks.
• Understanding ML, DNNs, NLP, or Speech Recognition.
• Empirical research mindset: form hypotheses, calibrations, iterations.
• Strong communication and interpersonal skills in a distributed team.
• Mentoring junior engineers and interns is a plus.
• Desire to grow and learn; strong CS fundamentals in algorithms and distributed computing.

Responsibilities

• Design and evaluate routing policies for LLM traffic to best use mixture of model systems.
• Build and run agentic benchmarks and turn results into calibration data and routing profiles.
• Collaborate with engineering teams across NVIDIA to ensure seamless integration within the serving stack.

Skills

DL frameworks

PyTorch

TensorFlow

LLM benchmarks

Distributed systems

NLP

Research mindset

Communication

Education

Bachelors or Masters in CS

Tools

CUDA

GPU architecture

Linux

Job description

NVIDIA Corporation is seeking a Senior Research Engineer with a passion for Generative AI inference. You will help shape how AI is infused into products by developing optimized inferencing technologies and collaborating across research, engineering, and open-source communities.

Ideal candidates have 8+ years in deep learning frameworks (PyTorch or TensorFlow), strong CS fundamentals, and experience evaluating LLMs or agentic benchmarks.