Software Engineer, Agent Performance Modeling

What you'll do

• Build and validate performance models for LLM architectures across GPU, LPU, and heterogeneous systems.
• Develop agents to automate simulation workflows and analyze performance bottlenecks.
• Accelerate design space exploration for emerging LLM architectures.
• Collaborate with hardware, inference, runtime, and compiler teams to improve modeling accuracy.
• Guide hardware and software optimization decisions based on simulation results.
• Build reliable engineering tools using coding agents to automate complex workflows.

What we're looking for

• Completed a MS in Computer Science or a related field, or equivalent 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 and a rigorous approach to experimentation and validation.
• Experience building reliable engineering tools using coding agents.
• Experience building agents that automate complex engineering workflows (preferred).
• Knowledge of accelerator architecture and compute, memory, or communication bottlenecks (preferred).
• Open-source contributions in agentic systems, simulation, or inference optimization (preferred).