Software Development Engineer - Generative AI, AGIF Inference Engine

Are you interested in advancing Amazon's Generative AI capabilities? Come work with a talented team of engineers and scientists in a highly collaborative and friendly team. We are building state-of-the-art Generative AI technology that will benefit all Amazon businesses and customers.

Key job responsibilities

As a Software Development Engineer, you will be responsible for designing, developing, testing, and deploying high performance model inference capabilities, including but not limited to multi-modality, SOTA model architectures, latency, throughput, and cost. You will collaborate closely with a team of engineers and scientists to influence our overall strategy, and define the teams roadmap. You will drive system architecture, spearhead best practices, and mentor junior engineers.

A day in the life

You will consult with scientists to get inspiration of emerging techniques, and blend those into our roadmap; You will design and experiment with new algorithms from public and internal papers, benchmark the latency and accuracy of your implementations; Most importantly you will implement production grade solutions, and see them through the deployments swiftly; You may need to collaborate with other science and engineering teams to get things done properly; You will hold highest bar in operational excellence and support production systems, and constantly create solutions to minimize the ops load.

About the team

Our mission is to build best-in-class, fast, accurate, and cost-efficient frontier model inference solutions and infrastructure that will enable Amazon businesses to deliver more value to their customers.

Basic Qualifications

- 3+ years of non-internship professional software development experience

- Must have one of the following two: 1) Prior experience with software performance optimization Or 2) Knowledge of Deep Learning and Transformer architectures

Preferred Qualifications

- 3+ years of full software development life cycle, including coding standards, code reviews, source control management, build processes, testing, and operations experience

- Bachelor's degree in computer science or equivalent

- Experience with Large Language Model Inference

- Experience with GPU programming (TensorRT-LLM)

- Experience with Python, PyTorch, and C++ programming and performance optimization

- Experience with Trainium and Inferentia Development

Amazon is an equal opportunity employer and does not discriminate on the basis of protected veteran status, disability, or other legally protected status.

Our inclusive culture empowers Amazonians to deliver the best results for our customers. If you have a disability and need a workplace accommodation or adjustment during the application and hiring process, including support for the interview or onboarding process, please visit for more information. If the country/region youre applying in isnt listed, please contact your Recruiting Partner.

Our compensation reflects the cost of labor across several US geographic markets. The base pay for this position ranges from $129,300/year in our lowest geographic market up to $223,600/year in our highest geographic market. Pay is based on a number of factors including market location and may vary depending on job-related knowledge, skills, and experience. Amazon is a total compensation company. Dependent on the position offered, equity, sign-on payments, and other forms of compensation may be provided as part of a total compensation package, in addition to a full range of medical, financial, and/or other benefits. For more information, please visit . This position will remain posted until filled. Applicants should apply via our internal or external career site.