Software Development Manager, LLM Inference Model Enablement, Neuron SDK
Core
Lead a team of AI/ML engineers to onboard and optimize state-of-the-art open-source and customer LLMs (dense and MoE) for inference on AWS Trainium accelerators.
Role type
Senior IC Software Development Manager (LLM Inference)
Builds
High-performance LLM inference solutions on Trainium hardware
Domain
Cloud-scale machine learning accelerators / LLM inference
Deliverable
production ML models
Required skills
LLM model architectures, model performance optimizations, inference techniques, distributed inference libraries, system design patterns, reliability and scaling
Preferred skills
Technical leadership, recruiting and hiring, mentoring/coaching, product strategy communication
Technologies
PyTorch inference library, Neuron compiler, Neuron runtime, collectives
Responsibilities
Manage day-to-day engineering team activities, execute project plans and delivery commitments, manage resources and staffing, report on development status and model performance, define model enablement and performance optimization strategies
Seniority
Senior, hands-on IC with management responsibilities
