Senior AI/ML Performance Engineer
Minimum qualifications:
- Bachelor’s degree or equivalent practical experience.
- 5 years of experience with software development in one or more programming languages.
- 3 years of experience with one or more of the following: Speech/audio (e.g., technology duplicating and responding to the human voice), reinforcement learning (e.g., sequential decision making), ML infrastructure, or specialization in another ML field.
- 3 years of experience with ML infrastructure (e.g., model deployment, model evaluation, optimization, data processing, debugging).
- Experience with AI and agentic tooling for development and research.
- Master's degree or PhD.
- 5 years of experience with data structures/algorithms in C++ and Python.
- Experience with an emphasis on algorithms, systems and tools for ML performance projections and evaluation.
- Experience designing or implementing components of a Deep Learning Compiler Stack (e.g., XLA, MLIR, TVM, ONNX Runtime).
- Experience in low-latency systems programming (e.g., C/C++) and optimizing data movement across the memory hierarchy (e.g., caches, HBM, I/O).
- Experience in performance engineering for ML/AI, including the design and optimization of GPU/TPU kernels, deep learning compilers, or low-latency systems infrastructure.
- Design and implement solutions in one or more specialized ML areas, leverage ML infrastructure, and demonstrate expertise in a chosen field.
- Build, maintain and validate HW/SW tooling to enable reliable and fast evaluation of options and solutions for ML/AI infrastructure (C++, Python).
- Build and maintain tools and methods to measure, visualize and analyse ML HW/SW performance.
- Define, implement and validate performance and cost metrics relevant for existing and future workloads and systems.
- Collaborate with other teams (hardware, compiler, ML research) to improve the end to end flow and results.