Amazon
Join the dynamic Machine Learning Inference Model Enablement team at AWS Neuron, where we empower developers to optimize and enhance the performance of large language models and other advanced AI frameworks. As a Senior Software Development Engineer, you'll play a pivotal role in building and tuning distributed inference solutions on cutting-edge machine learning accelerators.
Key Responsibilities:
Lead the development of distributed inference support for Pytorch within the Neuron SDK.
Tune and optimize various model families, including Llama, DeepSeek, and vision transformers for maximum performance on AWS Trainium and Inferentia.
Collaborate closely with compiler and runtime engineers to drive innovations in the machine learning inference stack.
Create metrics and automation processes to enhance software architecture and resolve defects.
Engage in design discussions, code reviews, and communicate effectively with team members and stakeholders.
What We Are Looking For:
We seek candidates with a blend of strong software development skills using Python and a solid understanding of machine learning concepts. Your experience in optimizing inference performance on large models is essential.
Basic Qualifications:
5+ years of professional software development experience.
5+ years of experience in design or architecture of systems, including reliability and scaling.
Familiarity with machine learning fundamentals, LLM architectures, and optimizations for model execution.
Proficiency in at least one programming language.
Preferred Qualifications:
5+ years of full software development lifecycle experience, spanning coding standards to operations.
Master’s degree in computer science or a related field.
Our team fosters knowledge-sharing and mentorship, promoting your career growth while tackling impactful challenges. If you are passionate about AI/ML and eager to work in a collaborative, startup-like environment, we would love to meet you!
Location: Please refer to the job posting for the specific work address.