Description
NVIDIA is revolutionizing the computing industry by harnessing the power of AI. As an NVIDIAN, you'll work in an inclusive environment that encourages innovation and excellence. We're seeking an AI Systems Engineer to join our team, focusing on designing efficient AI systems by combining simulation and agentic engineering.
Job Overview: You'll build and validate performance models for large language model (LLM) architectures across various systems, develop agents to automate simulation workflows, and collaborate with cross-functional teams to enhance modeling accuracy and optimize system performance.
Responsibilities:
- Develop performance models for LLM architectures on GPU, LPU, and heterogeneous systems
- Create agents to automate simulation workflows, analyze bottlenecks, and accelerate design space exploration
- Collaborate with hardware architecture, inference, runtime, and compiler teams to improve modeling accuracy and guide optimization
Requirements:
- Master's degree in Computer Science or a related field, or equivalent experience
- Familiarity with modern LLM architectures and inference characteristics
- Experience with simulation, profiling, or performance modeling, including roofline analysis for LLM inference
- Strong analytical skills and a rigorous approach to experimentation and validation
- Experience building reliable engineering tools using coding agents
Nice to Have:
- Experience building agents that automate complex engineering workflows
- Knowledge of accelerator architecture and compute, memory, or communication bottlenecks
- Open-source contributions in agentic systems, simulation, or inference optimization
Compensation: Your base salary will be between 124,000 USD and 241,500 USD, depending on your location, experience, and position level. You'll also be eligible for equity and benefits.