Senior/Staff Backend Compiler Engineer

📋 Description

• • Join Axelera AI, a pioneering deep-tech startup revolutionizing the AI landscape with our groundbreaking Metis™ AI Platform, and contribute to the future of artificial intelligence.
• • As a Senior/Staff Backend Compiler Engineer, you will be a pivotal member of our Compiler team, playing a crucial role in enhancing our in-house domain-specific language (DSL) and its surrounding compiler infrastructure.
• • Your primary focus will be on elevating the kernel-developer experience, making it exceptionally seamless and user-friendly, thereby democratizing access to our advanced AI capabilities.
• • You will be instrumental in optimizing our compiler backend, ensuring efficient mapping of high-level AI workloads onto our sophisticated heterogeneous hardware architecture.
• • This involves deep dives into optimizing compute performance, managing memory usage effectively, and orchestrating data movement across complex multi-level memory hierarchies and specialized accelerators.
• • Collaborate closely with a world-class, distributed team of engineers across Europe, operating at the dynamic intersection of compilers, computer architecture, and high-performance computing.
• • This is a unique opportunity to work on cutting-edge AI hardware, exert significant influence over core compiler design decisions, and make a tangible impact within a rapidly evolving startup environment.
• • Take ownership of evolving our proprietary kernel language, transforming it into a versatile tool accessible to both internal developers and external partners, fostering broader adoption and innovation.
• • Design, develop, and implement advanced backend compiler optimizations tailored for efficient workload execution on heterogeneous architectures, encompassing CPUs, NPUs, and specialized accelerators.
• • Implement sophisticated optimization strategies across the entire compiler stack, leveraging your expertise in areas such as memory planning, tiling, vectorization, task partitioning, and concurrency optimizations for both compute and memory operations.
• • Actively contribute to the development and refinement of the compiler infrastructure, including intermediate representations (IRs) and critical optimization passes, ensuring robustness and performance.
• • Conduct in-depth analysis of performance bottlenecks, identifying root causes and implementing targeted improvements through rigorous profiling and benchmarking.
• • Play a key role in shaping the technical direction of the compiler team, providing mentorship to junior engineers, and championing the adoption of engineering best practices to foster a culture of excellence.
• • Thrive in a highly collaborative, distributed engineering environment, contributing to a shared vision and collective success.
• • Contribute to the development of tools and frameworks that enhance the productivity of AI developers working with our platform.
• • Engage in the full software development lifecycle, from design and implementation to testing and deployment of compiler components.
• • Stay abreast of the latest advancements in compiler technology, computer architecture, and AI hardware, integrating new insights into our development process.
• • Participate in code reviews, providing constructive feedback to peers and ensuring high-quality code standards.
• • Help define and document compiler APIs and usage guidelines for internal and external stakeholders.
• • Contribute to the strategic roadmap of the compiler team, aligning technical efforts with the company's overall objectives.
• • Drive innovation by exploring and prototyping novel compiler techniques and optimization strategies.
• • Ensure the reliability and stability of the compiler through comprehensive testing and validation.
• • Work on performance-critical code paths, ensuring maximum efficiency and minimal latency.
• • Understand and address the unique challenges of compiling for specialized AI hardware, bridging the gap between high-level programming models and low-level hardware execution.
• • Contribute to a culture of continuous learning and knowledge sharing within the engineering organization.
• • Be a key player in Axelera AI's mission to accelerate AI development and deployment globally.