Software Development Manager • Lead

Who you are

You have a strong background in LLM model architectures and performance optimizations — you've successfully onboarded and optimized various state-of-the-art models for inference on cloud-scale systems. Your experience with distributed inference libraries allows you to deliver high-performance models that meet demanding requirements.

You possess excellent leadership skills and are capable of managing fast-changing priorities — you thrive in environments where you can drive improvements in model enablement speed and usability. Your technical ability to understand vertically integrated system stacks, including the PyTorch inference library and Neuron compiler, sets you apart.

You are a collaborative team player who enjoys working with senior management and technical leaders — you understand the importance of defining model enablement and performance optimization strategies for the latest LLMs. Your ability to communicate effectively with both technical and non-technical stakeholders is a key asset.

Desirable

Experience with automation tools and infrastructure optimization is a plus — you are familiar with the latest trends in AI/ML and are eager to implement innovative solutions that enhance model performance. A background in cloud computing and familiarity with AWS services will further strengthen your candidacy.

What you'll do

As the Software Development Manager for the LLM Inference Model Enablement team, you will lead a group of expert AI/ML engineers — your primary responsibility will be to onboard and optimize open-source and customer LLMs for inference on Neuron and Trainium accelerators. You will drive improvements in model enablement speed and experience, ensuring high-quality inference features and infrastructure.

You will collaborate closely with your team to define and implement strategies for optimizing model performance — this includes working with distributed inference libraries and enhancing the usability of inference tools. Your role will involve setting clear objectives and guiding your team through the complexities of AI/ML model deployment.

You will also be responsible for managing project timelines and ensuring that your team meets demanding deadlines — your leadership will be crucial in navigating the fast-paced nature of AI/ML development. You will engage in regular discussions with senior management to align on project goals and deliverables.

What we offer

At Amazon, you will be part of a dynamic team that is at the forefront of AI/ML innovation — we provide a collaborative environment where your contributions will directly impact the future of machine learning technologies. You will have access to a comprehensive benefits package, including medical, financial, and other perks that support your well-being.

We encourage you to apply even if your experience doesn't match every requirement — we value diverse perspectives and are committed to fostering an inclusive workplace. Join us in shaping the future of cloud-scale machine learning and make a difference in the industry.