Software Development Manager - Compiler

Salary: $212,700 - 287,700 per year Requirements:

• We need 5 years of engineering team management experience.
• We need 9 years of direct experience working within engineering teams.
• We need 4 years of experience designing or architecting new and existing systems, including patterns for reliability and scaling.
• We need experience collaborating with product or program management teams.
• We need deep expertise in compilers, including resource management, instruction scheduling, code generation, and compute graph optimization.
• We need strong software design foundations and excellent system-level coding ability, with emphasis on graph theory and performance techniques.
• A PhD in computer science, computer engineering, or a related field, or an MS degree, is preferred.
• Experience troubleshooting or debugging hardware is preferred.
• Experience developing and deploying large language models in production on GPUs, Neuron, TPU, or other AI acceleration hardware is preferred.
• Experience with XLA, TVM, MLIR, LLVM, deep learning models and algorithms, and deep learning framework design is preferred.
• Leadership or active contribution within open-source communities is preferred.
• We need candidates to be currently located in, or willing to relocate to, Cupertino, Seattle, or Austin.

• We will lead a team of experienced compiler engineers building optimization algorithms and deploying a new compiler for our custom AWS hardware at scale.
• We will partner closely with AWS ML services teams as technical collaborators, including work tied to pre-silicon design and bringing new products and features to market.
• We will apply our knowledge of resource management, scheduling, code generation, and optimization to advance deep learning compiler technology.
• We will help develop software that improves performance and productivity for the deep learning community.
• We will communicate effectively as a trusted technical manager and contribute directly as a hands-on partner when needed.

• AI
• AWS
• Hardware
• LLVM
• Machine Learning
• PyTorch
• Cloud
• Flow
• GitHub
• Support

More:

We are building AWS Machine Learning accelerators, including Inferentia for low-cost, high-performance inference and Trainium for high-performance ML training. Our edge software stack, the AWS Neuron SDK, includes an ML compiler and runtime with native integration into frameworks such as PyTorch and JAX, and it is used at scale by customers and partners across many industries. You would join the Amazon Annapurna Labs team, where we build silicon and software innovation for AWS customers in a small, agile, and highly collaborative environment. We value inclusion, mentorship, career growth, and work-life balance, and we offer comprehensive benefits including health coverage, retirement matching, paid time off, parental leave, and additional compensation components such as sign-on payments and RSUs. This role is based in Cupertino, Seattle, or Austin, with Cupertino preferred.

last updated 35 week of 2026