GPU Performance Modeling & Optimization Engineer

Responsibilities

• Perform pre-silicon performance modeling using cycle-accurate or cycle-approximate simulators for GPU subsystems.
• Execute microarchitectural exploration to evaluate GPU configurations, scaling limits, and trade-offs.
• Profile and optimize performance for advanced generative AI, LLM topologies, and traditional graphics pipelines.
• Lead post-silicon characterization and correlate hardware-software execution results back to pre-silicon models.
• Root-cause hardware-software mismatches using low-level performance counters and Linux tracing frameworks.
• Partner with compiler, runtime, and software framework teams to implement architectural optimizations.

Requirements

• B.E. / B.Tech. / M.Tech. degree.
• 5 to 10 years of industry experience in silicon performance engineering, GPU modeling, or microarchitecture design.
• Deep technical knowledge of GPU architecture, including execution pipelines, SIMD/SIMT models, and cache hierarchies.
• Expert proficiency in modern C++ and production-grade Python.
• Hands-on experience with performance modeling and hardware simulators.
• Strong understanding of AI/Compute workloads, including LLM scaling and parallel training/inference strategies.

Preferred Qualifications

• Experience with modern programmable graphics pipelines and compute shader mechanics.
• Proven capability in extracting and analyzing low-level hardware performance counters in a lab environment.
• Ability to translate complex simulation or silicon data into actionable technical findings for stakeholders.

About the Company

AMD is a global leader in high-performance computing, graphics, and visual technologies. Our mission is to build great products that accelerate next-generation computing experiences—from AI and data centers to PCs, gaming, and embedded systems.