Description
We are looking for a Deep Learning Compiler Engineer to join our team. As a member of our Deep Learning Compiler (DLC) team, you will be responsible for analysing deep learning networks and developing compiler optimisation algorithms. You will collaborate with members of the deep learning software framework teams and the hardware architecture teams to accelerate the next generation of deep learning software.
Your scope of work will include defining public APIs, performance optimisations and analysis, crafting and implementing compiler infrastructure techniques for neural networks, and other general software engineering work.
To be successful in this role, you will need a strong background in computer science, computer engineering, or a related field, and at least 3 years of relevant work or research experience in performance analysis and compiler optimisations. You will also need excellent C/C++ and Python programming and software design skills, including debugging, performance analysis, and test design.
Responsibilities:
- Analyse deep learning networks and develop compiler optimisation algorithms
- Collaborate with members of the deep learning software framework teams and the hardware architecture teams to accelerate the next generation of deep learning software
- Define public APIs, performance optimisations and analysis, craft and implement compiler infrastructure techniques for neural networks, and other general software engineering work
Requirements:
- Bachelor's, Master's or Ph.D. in Computer Science, Computer Engineering, or a related field
- At least 3 years of relevant work or research experience in performance analysis and compiler optimisations
- Excellent C/C++ and Python programming and software design skills, including debugging, performance analysis, and test design
- Strong interpersonal skills and ability to work in a dynamic product-oriented team
Preferred qualifications:
- Proficient in CPU and/or GPU architecture
- CUDA or OpenCL programming experience
- Experience with systems with constrained resources, such as embedded platforms, small memory size, and cross compilation
- Experience with the following technologies: MLIR, XLA, TVM, LLVM, deep learning models and algorithms, and deep learning frameworks, such as PyTorch
- GPU kernel generation with high performance and fast build time
- A track record of success in mentoring junior engineers and interns