DC-GPU Performance Modeling Engineer

The Team:

AMD's Data Centre GPU Performance organization is transforming the industry with our AI based Graphic Processors. Our primary objective is to design exceptional products that drive the evolution of computing experiences, serving as the cornerstone for enterprise Data Centres for AI/ML workload.

The Role:

Architect, analyse and optimize high-performance GPU-centric SoCs for Machine Learning workload. Develop performance models and methodologies. Propose solutions to enhance performance and optimize power for next-generation data centre systems.

The Person:

As a system performance architect on our design engineering team, you will help propose and implement solutions to our next generation GPU SoCs and optimize data centre system application performance.

Key Responsibilities:

- Define, build and maintain performance models for performance projections, analysis and architecture exploration.
- Develop and execute system-level modelling strategies for ML and GPU hardware and software co-design.
- Drive performance trade-off studies for current architectural features, algorithms, and system configurations, providing data-driven recommendations.
- Collaborate with architecture, design and software teams to integrate models, define workloads and analyse simulation results.
- Innovate and advance modelling methodologies,



tools and infrastructure to improve accuracy, speed, and architectural insight.

PREFERRED EXPERIENCE:

- Strong understanding of computer architecture. Experience of working in GPUs, SoCs, ML accelerators would be a plus.
- Exposure to performance analysis, workload characterization, and hardware/software co-design exploration.
- Familiarity with ML models and software stacks relevant to ML
- Understanding of AI model distributed training and inference, model layers and ML ops, parallelization strategies
- Understanding of system-level modelling and simulation will be a plus.
- Strong programming skills, including experience with Python (or similar)

ACADEMIC CREDENTIALS:

- Ph.D. in Computer Science / Electronics Engineering, and 1+ years of experience as a Performance Engineer
- M.S./M.Tech. in Computer Science / Electronics Engineering, and 3+ years of experience as a Performance Engineer
- B.Tech. in Computer Science / Electronics Engineering, and 5+ years of experience as a Performance Engineer

Disclaimer : This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.

📌 DC-GPU Performance Modeling Engineer (Karnataka)
🏢 Advanced Micro Devices (AMD)
📍 Karnataka