Senior Deep Learning Compiler Engineer – XLA

This is a fully remote position, open to applicants in California, +2 more states.

📋 Description

• Create optimization algorithms for compilers tailored for deep learning tasks.

• Enhance both inference and training performance for the JAX framework and OpenXLA compiler on NVIDIA GPUs at scale.

• Collaborate with partners in deep learning frameworks and teams focused on hardware architecture.

• Develop and apply compiler optimization strategies for deep learning network graphs.

• Design techniques for graph partitioning and tensor sharding to facilitate distributed training and inference.

• Conduct performance tuning and thorough analysis.

• Execute code generation for NVIDIA GPU backends utilizing MLIR, LLVM, and OpenAI Triton.

• Create user-facing features within JAX and its associated libraries.

• Engage in general software engineering tasks.

• Partner with GPU hardware engineering teams to devise AI compiler software features for future-generation GPUs.

• Establish project objectives and scope while leading development initiatives.

• Implement software engineering and testing methodologies.

• Guide junior engineers and interns through mentorship.

⛳️ Requirements

• A Bachelor's, Master's, or Ph.D. in Computer Science, Computer Engineering, or a related field, or equivalent experience.

• At least 4 years of relevant work or research experience focused on performance analysis and compiler optimizations.

• Ability to operate independently, define project goals and scope, and lead development projects.

• Proficient in clean software engineering and testing practices.

• Exceptional skills in C/C++ programming and software design.

• Experience in debugging, performance analysis, and test design.

• Strong understanding of CPU, GPU, or other high-performance hardware accelerator architectures.

• Familiarity with high-performance computing and distributed programming.

• Experience with CUDA or OpenCL programming is desirable but not mandatory.

• Experience with XLA, TVM, MLIR, LLVM, OpenAI Triton, deep learning models and algorithms, or the design of deep learning frameworks is advantageous.

• Excellent interpersonal skills and the ability to thrive in a dynamic, product-focused team environment.

• Experience with JAX, PyTorch, or TensorFlow; familiarity with CUDA or GPUs; and knowledge of open-source compilers such as XLA, LLVM, MLIR, or TVM will set candidates apart.

🏝️ Benefits

• Competitive salaries.

• Comprehensive benefits package.

• Equity opportunities.

• Additional benefits.