Senior Software Engineer, Agent Simulation and Evaluation

About the role

NVIDIA is a technology company developing GPU- and AI-powered computing systems for computers, robots, and self-driving cars. The Senior Software Engineer will build agentic systems and tools for simulation, evaluation, performance analysis, and reporting of emerging AI workloads across GPU, LPU, and heterogeneous systems. The role will collaborate with cross-functional engineering teams and automate benchmarking, workload characterization, capacity planning, and release qualification workflows.

Responsibilities

• Building agentic systems that automate simulation, evaluation, performance analysis, and reporting
• Developing tools that configure experiments, run evaluations, analyze results, identify regressions, and recommend follow-up work
• Analyzing the inference characteristics of LLMs, reasoning models, coding agents, multimodal models, and agentic harnesses
• Building and validating performance models for GPU, LPU, and heterogeneous GPU–LPU systems
• Collaborating with inference, hardware, runtime, compiler, evaluation, and product teams to improve simulation quality and accelerate engineering decisions
• Automating critical LPU workflows such as benchmarking, workload characterization, capacity planning, and release qualification