Senior Software Engineer, Agent Performance Modeling
$152k - $288k • US, CA, Santa Clara
Posted 10d ago
Job Location
US, CA, Santa Clara
Tech Stack
Remote Work Policy
On-site
Categories
AI Agent Engineer
About the job
NVIDIA is at the forefront of AI, powering the next era of computing with its GPUs. This role focuses on understanding how evolving Large Language Model (LLM) architectures and inference workloads map to hardware, which is critical for designing efficient AI systems. The team utilizes simulation and agentic engineering to analyze emerging architectures and inform hardware and software development decisions.
Responsibilities
- Build and validate performance models for LLM architectures across various hardware systems.
- Develop agents to automate simulation workflows, analyze bottlenecks, and explore design spaces.
- Collaborate with hardware architecture, inference, runtime, and compiler teams to enhance modeling accuracy and guide optimizations.
Requirements
- MS in Computer Science or related field with 5+ years of 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 with a rigorous approach to experimentation and validation.
- Strong software engineering skills and experience building reliable engineering tools using coding agents.
Benefits
- Equity
- Benefits