Neuron Runtime Software Development Engineer , Neuron Runtime
Core
Develop and maintain high-performance runtime libraries, drivers, and profilers for AWS Inferentia and Trainium ML accelerators to optimize AI workloads.
Role type
Senior IC software development engineer (runtime systems & ML infrastructure)
Builds
Neuron Runtime, ML kernels, and profiling tools for Trainium and Inferentia devices
Domain
Cloud-scale machine learning infrastructure and custom hardware acceleration
Deliverable
production ML models | infrastructure
Required skills
C++ programming, distributed systems architecture, high availability design, fault tolerance, AWS services (EC2, ECS, CloudWatch, S3, Lambda), end-to-end service ownership, compiler integration, multi-framework support (PyTorch, JAX, XLA)
Preferred skills
Full SDLC experience, code review leadership, build process automation, testing strategies, operations experience
Technologies
C++, PyTorch, JAX, XLA, AWS (EC2, ECS, CloudWatch, S3, Lambda)
Responsibilities
Design and develop runtime libraries and drivers for ML accelerators, manage the full development lifecycle of Neuron Runtime, collaborate on C++ compiler integration for performance insights, drive innovations for profiler support across multiple frameworks, ensure scalability and reliability of distributed systems
Seniority
Senior, hands-on IC