Senior Software Engineer, Agent Simulation and Evaluation
NVIDIAJob Title
Senior Software Engineer, Agent Simulation and Evaluation
Role Summary
Work on simulation, evaluation, and performance-analysis tooling for agentic AI and inference workloads in the LPU organization. The role focuses on building agent-driven systems that automate experiments, profiling, and decision-making to inform hardware and software trade-offs.
The team collaborates with inference, hardware, runtime, compiler, evaluation, and product groups to accelerate engineering decisions across GPU and LPU platforms.
Experience Level
Senior — requires substantial prior experience. This posting requests 5+ years of relevant software development experience and at least 2 years building AI agents or AI-backed engineering systems.
Responsibilities
Primary responsibilities include designing and implementing tools and systems to evaluate and model inference workloads and to automate engineering workflows.
- Build agentic systems that automate simulation, evaluation, performance analysis, and reporting.
- Develop tooling to configure experiments, run evaluations, analyze results, detect regressions, and recommend follow-up work.
- Analyze inference characteristics of LLMs, reasoning models, coding agents, multimodal models, and agentic harnesses.
- Build and validate performance models for GPU, LPU, and heterogeneous GPU–LPU systems.
- Collaborate with inference, hardware, runtime, compiler, evaluation, and product teams to improve simulation quality and speed decisions.
- Automate LPU workflows such as benchmarking, workload characterization, capacity planning, and release qualification.
Requirements
Must-have technical skills and experience for immediate contribution.
- 5+ years of software development experience building production engineering tools or systems.
- At least 2 years building AI agents or AI-backed engineering systems.
- Strong Python skills and experience delivering reliable engineering tools.
- Experience evaluating AI models or agents and analyzing performance.
- Experience with simulation, profiling, benchmarking, or performance modeling.
- Familiarity with modern model architectures and AI inference workloads.
Nice-to-have:
- Experience using coding agents (e.g., Codex, Claude Code) to automate technical workflows.
- Knowledge of GPU/accelerator architecture, distributed inference, or high-performance computing.
- Open-source contributions showing agentic AI, evaluation, or performance-engineering work.
- Rigorous analytical approach to experimentation, data collection, and validation.
Education Requirements
MS in Computer Science, Engineering, or a related field, or equivalent practical experience.
About the Company
Company: NVIDIA
Headquarters: Santa Clara, California, USA
NVIDIA is a global leader in accelerated computing, renowned for its innovative solutions in AI and digital twins that transform diverse industries. The company specializes in networking technologies, providing end-to-end InfiniBand and Ethernet solutions for servers and storage that optimize performance and scalability. NVIDIA serves sectors such as high-performance computing, enterprise data centers, and cloud computing, constantly reinventing its products and services to stay ahead in the market.
