Position Details
About this role
Runtime Software Development Engineer for AWS Neuron focusing on high-performance Linux drivers and HPC libraries to accelerate AI workloads on Inferentia. Builds distributed runtime software and collaborates with ML teams to optimize performance and scale.
Key Responsibilities
- Design, develop, and deploy runtime software for AWS Neuron on Inferentia
- Develop high-performance Linux drivers and HPC libraries (libfabric, MPI)
- Collaborate with ML scientists to optimize performance
- Mentor and review code; uphold coding standards and testing
- Deliver scalable, fault-tolerant runtime systems for customers
Technical Overview
Expertise in Linux drivers, libfabric, MPI, and ML frameworks (TensorFlow, PyTorch, MXNet) in C/C+/Python; develops for distributed, embedded runtimes targeting AI accelerators; integrates with AWS Inferentia hardware.
Ideal Candidate
The ideal candidate is a mid-level runtime software engineer with 3+ years building distributed ML systems, strong Linux driver experience, and hands-on work with ML frameworks (TensorFlow, PyTorch, MXNet). They should excel at optimizing performance for AI accelerators and collaborate across teams to deliver scalable runtimes on AWS Inferentia.
Must-Have Skills
Nice-to-Have Skills
Tools & Platforms
Required Skills
Hard Skills
Soft Skills
Industry & Role
Keywords for Your Resume
Deal Breakers
No Linux driver experience, No ML framework experience, No distributed systems experience, No experience with cloud platforms
Get matched to jobs like this
Luna finds roles that fit your skills and career goals — no endless scrolling required.
Create a Free Profile