ML Compiler Engineer, TPU Performance Optimizations
Bengaluru, Karnataka, Indiaonsitefull timeToday
Responsibilities:
Learn and build an intuitive understanding of various parts of Google’s ML stack: Frameworks (e.g., JAX, PyTorch), XLA and runtime stack.
Research and develop the novel compiler optimizations targeting ML workloads, and emerging architectures.
Identify opportunities to improve the efficiency of the ML workloads through insightful performance debugging for ML workloads and custom kernels, and build compiler solutions to deliver those improvements.
Provide technical leadership and mentorship as a Team Lead (TL), and explore strategic initiatives.
Minimum qualifications:
Bachelor's degree or equivalent practical experience.
8 years of experience in software development.
3 years of experience with software design and architecture.
Experience with machine learning, compilers, computer architecture, GPU programming, C++, Python.
Preferred qualifications:
Experience in open-source software development, including experience in releasing and supporting open-source projects.
Experience with state-of-the-art ML compilers and their internals, experience writing compiler optimization passes.
Comfortable with accelerator Hardware (HW) architectures (TPUs/Graphics Processing Unit (GPUs)).
Experience with debugging correctness and performance issues at all levels of the ML Software (SW) stack.
Hands-on experience with GPU or TPU performance analysis.
Comfortable debugging correctness and performance issues at all levels of the stack.
Ready to apply?
Sign up first — takes a minute — and you get Hiro’s take on this role, a resume tailored to it, and (if available) a referral from a real employee at Google. All free with your Pro gift.
Sign up to apply