Senior AI Agent Simulation Engineer - Performance Inference

NVIDIA AI; Santa Clara (CA); On-site; USD 180,000 - 260,000; Full time

Benefits offered by this job

Equity

Job summary

NVIDIA AI is seeking a software engineer to build agentic systems that automate simulation, evaluation, and performance analysis for AI workloads across GPU and LPU platforms.

You will collaborate with cross-functional teams, optimize inference characteristics, and automate critical engineering workflows such as capacity planning and release qualification.

Qualifications

• Master's degree required in CS/Engineering.
• Over 5 years of software development experience, including 2 years building AI agents.
• Proficient in Python and experienced with AI inference workloads and performance modeling.

Responsibilities

• Build agentic systems to automate simulation, evaluation, and performance analysis for AI workloads.
• Collaborate with cross-functional teams to optimize inference characteristics and automate critical workflows in engineering (capacity planning, release qualification).

Skills

AI Agents

Python

Model Architectures

Performance Analysis

Simulation

Profiling

Benchmarking

Performance Modelling

GPU Architecture

LPU Systems

Distributed Inference

High-Performance Computing

LLMs

Reasoning Models

Multimodal Models

Engineering Tools

Education

Master's degree in Computer Science or Engineering

Job description

Build agentic systems to automate simulation, evaluation, and performance analysis for AI workloads across GPU and LPU platforms. Collaborate with cross-functional teams to optimize inference characteristics and automate critical engineering workflows like capacity planning and release qualification.

Requirements: Requires a Master's degree in Computer Science or Engineering and over 5 years of software development experience, including 2 years specifically building AI agents. Candidates must be proficient in Python and have experience with AI inference workloads and performance modeling.

Key Skills: AI Agents, Python, Model Architectures, Performance Analysis, Simulation, Profiling, Benchmarking, Performance Modelling, GPU Architecture, LPU Systems, Distributed Inference, High-Performance Computing, LLMs, Reasoning Models, Multimodal Models, Engineering Tools

Benefits: Equity