Position Overview
Axelera AI is seeking a talented Senior/Staff Engineer – Computing Architecture to design and develop the next generation of AI computing systems. In this critical role, you will work closely with hardware, software, and product teams to define architectural requirements, optimize system performance, and ensure scalability for our AI solutions. As a Computing Architecture Engineer, you will contribute to the conceptualization, specification, and implementation of advanced computing architectures, enabling Axelera AI to deliver cutting-edge solutions that meet the demanding needs of our customers.
Key Responsibilities
- Architecture Design: Define and develop computing architectures for AI accelerators.
- Performance Optimization: Analyze and optimize computational workloads, ensuring low power consumption, high efficiency, and maximum performance for AI applications.
- Technology Leadership: Drive innovation in architectural design by evaluating emerging technologies, industry trends, and academic advancements.
- Cross-Functional Collaboration: Work with hardware, software, and product teams to translate system requirements into architectural solutions that balance performance, cost, and power.
- System Modeling & Tooling Development: Develop simulation and modeling tools to validate architectural designs and predict system performance across target AI workloads.
- Mentorship: Provide technical guidance and mentorship to junior engineers, fostering a culture of excellence and innovation within the team.
Qualifications
- Master’s or PhD in Computer Engineering, Electrical Engineering, or a related field.
- 5+ years of experience in computing architecture or system design, preferably within AI, semiconductor, or computing domains.
- Strong expertise in AI accelerator designs, including neural processing units (NPUs) or graphics processing units (GPUs).
- Proficiency in architectural modeling, simulation tools, and performance analysis frameworks.
- Proficiency in Python or C++ programming with a strong understanding of language features and best practices.
- Deep understanding of state-of-the-art AI inference workloads, algorithms, and dataflow.
- Proven track record of delivering complex computing architectures from concept to implementation.
Preferred Skills
- Familiarity with the modern IC design flow from architecture to GDSII.
- Familiarity with parallel programming models, e.g. via CUDA or similar APIs.
- Experience with AI compilation frameworks such as MLIR and/or TVM.