Software Engineer, Agent Performance Modeling

Quick Facts

• Role: Software Engineer (New College Grad 2026) — Agent Performance Modeling
• Focus: LLM hardware performance modeling and simulation workflow automation
• Compensation: Base salary range (Level 2: $124,000–$195,500; Level 3: $152,000–$241,500), plus equity and benefits

Description

As LLM architectures and inference workloads evolve, mapping them to hardware is critical for designing efficient AI systems. This role combines simulation and agentic engineering to build and validate performance models, enabling better hardware and software decisions. You will develop agents that automate simulation workflows, analyze bottlenecks, and accelerate design space exploration.

Responsibilities

• Build and validate performance models for LLM architectures across GPU, LPU, and heterogeneous systems.
• Develop agents to automate simulation workflows, analyze bottlenecks, and accelerate design space exploration.
• Collaborate with hardware architecture, inference, runtime, and compiler teams to improve modeling accuracy and guide optimization.

Requirements

• Recently completed MS in Computer Science (or related field) or equivalent experience.
• Familiarity with modern LLM architectures and their inference characteristics.
• Experience with simulation, profiling, or performance modeling for LLM inference, including roofline analysis.
• Strong analytical skills and a rigorous approach to experimentation and validation.
• Experience building reliable engineering tools using coding agents.

Benefits

• Eligible for equity and benefits.
• Inclusive, encouraging work environment.