You will validate AI/ML compute stacks and end-to-end inference pipelines.
Responsibilities
Execute validation plans for AI/ML compute stacks involving HIP, CUDA, OpenCL, OpenVINO, ONNX Runtime, and TensorFlow/PyTorch integrations.
Validate end-to-end AI pipelines, including model conversion, inference runtimes, compilers/toolchains, kernel execution, memory transfer, and inference results.
Manage defects and execute validation processes within the software development life cycle.
Profile ML workloads across various frameworks.
Required Skills
5+ years of professional experience.
Strong fundamentals in Machine Learning, including Deep Learning, LLMs, and Recommender Systems.
Proficiency in Python programming.
Experience with PyTorch and TensorFlow.
Solid knowledge of Ubuntu and Yocto Linux environments.
Familiarity with ONNX-Runtime and ML workload profiling.
Knowledge of OpenCL.
Understanding of production software QA practices and methodologies.