
Senior Software Engineer, Agent Performance Modeling
Required skills
- LLM
- inference
- simulation
- profiling
- performance modeling
- roofline analysis
- analytical skills
- experimentation
- validation
- software engineering
Nice to have
- agentic engineering
- automation
- workflow
- accelerator architecture
- compute bottlenecks
- memory bottlenecks
Role summary
NVIDIA is seeking a Senior Software Engineer specializing in Agent Performance Modeling to work on AI systems, particularly LLM architectures and inference workloads. The role involves building and validating performance models for GPUs, LPUs, and heterogeneous systems, developing agents to automate simulation workflows, and collaborating with hardware and software teams. Candidates should have an MS in Computer Science or related field with 5+ years of experience, familiarity with LLM architectures, simulation, profiling, performance modeling, and strong software engineering skills. Experience with agentic engineering and accelerator architecture is a plus.
Today, NVIDIA is tapping into the unlimited potential of AI to define the next era of computing, an era in which our GPUs act as the brains of computers, robots, and self-driving cars that can understand the world. Doing what's never been done before takes vision, innovation, and the world's best talent. As an NVIDIAN, you'll be immersed in a diverse, encouraging environment where everyone is inspired to do their best work.
As LLM architectures and inference workloads evolve, understanding how they map to hardware is critical to designing efficient AI systems. Our team combines simulation and agentic engineering to understand emerging architectures and inform hardware and software decisions.
What you'll be doing:
- 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.
What we need to see:
- MS in Computer Science or a related field, with 5+ years of experience.
- Familiarity with modern LLM architectures and their inference characteristics.
- Experience with simulation, profiling, or performance modeling, including familiarity with roofline analysis for LLM inference.
- Strong analytical skills and a rigorous approach to experimentation and validation.
- Strong software engineering skills and experience building reliable engineering tools using coding agents like Claude Code, Codex, etc.
Ways to stand out from the crowd:
- 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.
NVIDIA is widely considered one of the technology world's most desirable employers. We have some of the most forward-thinking and hardworking people in the world working for us. If you're creative, analytical, and autonomous, we want to hear from you!
#LI-Hybrid
You will also be eligible for equity and benefits.
Applications for this job will be accepted at least until October 13, 2026.This posting is for an existing vacancy.
NVIDIA uses AI tools in its recruiting processes.
NVIDIA is committed to fostering an inclusive work environment and proud to be an equal opportunity employer. As we highly value diversity in our current and future employees, we do not discriminate (including in our hiring and promotion practices) on the basis of race, religion, color, national origin, gender, gender expression, sexual orientation, age, marital status, veteran status, disability status or any other characteristic protected by law.Sample NVIDIA interview questions
- 1
Design a system for a rock paper scissors game
system designmedium - 2
Implement a distributed data migration management platform.
system designmedium - 3
Design a Distributed Build System with Cross-Data Center Artifact Sharing
system designhard - 4
Design a distributed training system for a trillion-parameter language model
system designmedium - 5
Develop a distributed tracing system for tracking and debugging.
system designmedium
Get started to unlock a personalized interview prep pack for this role.
Similar roles
Software Engineer, OpenShellNVIDIA · Remote · Hybrid
Senior Solutions Architect, NVIDIA Cloud Partner OperationsNVIDIA · Remote · Hybrid- Research Software EngineerConvergent Research · Boulder, CO · Onsite
Software Engineer IIPariveda · Dallas, TX · Hybrid- Senior Software Engineer, DatabaseInfluxData · Remote · Remote
- Software Engineering Intern, Frontend (Summer 2027)Notion · New York, NY · Hybrid
