✦ Luna Orbit — AI & Machine Learning

Senior Software Development Engineer - AI/ML, AWS Neuron, Multimodal Inference

at Amazon.com

📍 US, WA, Seattle Unknown Posted March 13, 2026
Type Not Specified
Experience mid
Exp. Years Not specified
Education Not specified
Category AI & Machine Learning

This role involves developing and optimizing AI/ML inference solutions on AWS hardware accelerators, focusing on large language models and deep learning frameworks.

  • Architect and implement ML inference features
  • Optimize large language model performance
  • Collaborate with hardware and software teams
  • Support open source ecosystem integration
  • Mentor junior engineers

The position requires expertise in ML frameworks like PyTorch and JAX, hardware accelerators such as Inferentia and Trainium, and performance optimization for distributed inference.

The ideal candidate is a senior AI/ML engineer with extensive experience in deep learning frameworks, hardware accelerators, and distributed inference systems. They possess strong hardware knowledge and a track record of optimizing large-scale ML models for inference and training.

Deep learningML compilerML inferencePyTorchJAXperformance tuningdistributed inferencehardware knowledge
GenAIlarge language modelsLLMML trainingoptimizationKernelsOpen source ecosystems
AWS Neuron SDKPyTorchJAXInferentiaTrainium
AWSAmazon Web ServicesAWS NeuronML compilerruntimeapplication frameworkPyTorchJAXML inferenceML trainingdeep learningGenAIlarge language modelsLLMInferentiaTrainiumhardware-software boundarykernelsdistributed inferenceperformance tuning
AWSAmazon Web ServicesAWS NeuronML compilerruntimeapplication frameworkPyTorchJAXML inferenceML trainingdeep learningGenAIlarge language modelsLLMInferentiaTrainiumhardware-software boundarykernelsdistributed inferenceoptimizationperformance tuning
collaborationmentoringinfrastructure developmentinnovationproblem-solving
Industry Technology
Job Function Developing high-performance AI inference solutions on AWS hardware accelerators
AWSAmazon Web ServicesAWS NeuronML compilerruntimeapplication frameworkPyTorchJAXML inferenceML trainingdeep learningGenAIlarge language modelsLLMInferentiaTrainiumhardware-software boundarykernelsdistributed inferenceperformance tuninghardware knowledge

Lack of experience with AWS Neuron SDK, No hardware knowledge of Inferentia or Trainium, Insufficient experience in ML inference optimization

Apply for this Position →

Get matched to jobs like this

Luna finds roles that fit your skills and career goals — no endless scrolling required.

Create a Free Profile