Senior Staff Engineer- AI/ML Software & Compilers

Your Team, Your Impact

What You Can Expect

• As a Sr Staff Engineer - Machine Learning Software/Firmware Engineering you will influence and contribute to the architecture, design, and implementation of AI infrastructure and ML compiler for the Marvell Machine learning acceleration and Infrastructure. Work closely with Machine learning, networking and storage experts to develop compiler and runtime infrastructure to achieve the targeted features and performance benchmarks.

• With your in-depth technical knowledge, experience and understanding you will efficiently apply solutions to resolve complex technical problems. Creating state-of-the-art data center infrastructure solutions and IPs that make a significant impact on Marvell s Accelerated Compute mission.

• Architect, design and develop system software for reliable, scalable, high performing AI/ML systems using Python, C/C++.

• Design and develop the compiler, runtime and frameworks for Marvell ML Infrastructure and acceleration solutions.

• Evaluate code performance, debug, diagnose and drive resolution using advanced state of art technologies.

• Work on developing and enhancing the AI acceleration plugins for heterogeneous systems.

• Communicate and collaborate effectively with cross-functional hardware and software engineering teams.

• Develop software and troubleshoot issues related to hardware bring-up, multi-threaded software development with virtualized hardware.

• Hands on experience on hyperscale workloads such as Ranking and Recommendation Systems, Large Language Models, Retrieval-Augmented Generation, etc, accelerated by a broad range of custom compute, connectivity, storage, security technologies

• Develop and contribute to open frameworks such as LLVM, MLIR, OpenCL or OpenXLA.

• Plan, schedule, estimate efforts for projects and provide technical guidance to junior engineers during execution.

What Were Looking For

• BS/MS degree in: Computer Science, Computer Engineering, or Electrical Engineering
• Minimum 8-10 years of experience in architecting and developing compilers and system software.
• Must possess strong hands-on experience in C++ design and development principles.
• Experience designing and developing code on Python especially Python 3. x
• Understanding and working knowledge of CXL memory systems in Heterogeneous computing is a big plus.
• Hands on experience on hyperscale workloads such as Ranking and Recommendation Systems, Large Language Models, Retrieval-Augmented Generation, etc. , accelerated by a broad range of custom compute, connectivity, storage, security technologies
• Experience working with TensorFlow, PyTorch and JAX would be a big plus.
• Experience working on and contributing to an active compiler toolchain codebase, such as LLVM, MLIR, OpenCL or OpenXLA frameworks.
• Experience and familiarity with ML accelerators, GPU and ARM architectures is a plus.
• Experience with setting up AI/ML workloads and benchmarking, MLPerf or similar will be an added advantage.
• Comfortable in GIT, Jira and Confluence.
• Must have the ability to multi-task in a fast-paced environment where the workloads evolve at a rapid pace.