Software Engineer, Agent Performance Modeling - New College Grad 2026
NVIDIA· Engineer, Sys SW
Santa Clara, CA$124k - $195.5kfull-timePosted 4d ago
About the role
Role focused on building performance models for LLM architectures and developing agents to automate simulation workflows, with collaboration across hardware, inference, runtime, and compiler teams.
Responsibilities
- Building and validating performance models for LLM architectures across GPU, LPU, and heterogeneous systems.
- Developing agents to automate simulation workflows, analyze bottlenecks, and accelerate design space exploration.
- Collaborating with hardware architecture, inference, runtime, and compiler teams to improve modeling accuracy and guide optimization.
Qualifications
- Recently completed a MS in Computer Science or a related field, or equivalent experience.
- Familiarity with modern LLM architectures and their 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.
Skills
Required:Roofline analysisSimulation and performance modelingCoding agents / automation tooling
Benefits
- equity
- benefits
Last updated Oct 23, 2026. Interested? Apply on the company site.
About NVIDIA
World Leader in AI Computing
NVIDIA invents the GPU and drives advances in AI, HPC, gaming, creative design, autonomous vehicles, and robotics.
AIautonomous vehiclesgaminggpugraphics cardhigh performance computingliquid-ai-recruiting-targetllm
More open roles at NVIDIA
- Senior Physical Verification Engineer4d agoEngineer, ASIC
- Senior System Software Engineer, Display Security4d agoEngineer, Sys SW
- Senior FPGA Prototyping Engineer - Hardware4d agoSanta Clara, CA · Engineer, ASIC
- Senior Product Engineer4d agoHybrid (Thailand) · Engineer, Product Development
- Senior Architect - Data Processing Systems, Analytics and Data Intelligence4d agoHybrid (Remote / Local) · Architect