The role
From Amazon's own posting.
Are you interested in helping AWS customers by building ML-distributed systems to deploy Generative AI models for inferencing at scale? SageMaker is a fully managed service to prepare data and build, train, and deploy machine learning (ML) models for any use case with fully managed infrastructure, tools, and workflows. Specifically, the SageMaker Inference Platform enables customers to deploy ML models at scale to run high throughput, low-latency CPU/GPU/Inferentia workloads and monitor the quality of the models and data in production. The team is currently focused on solving core infrastructure problems for Generative AI inference serving needs of both internal and external customers. We're moving fast, and this is a great team to join and make a huge impact on AWS especially in the Generative AI space. To learn more about the product, please visit https://docs.aws.amazon.com/sagemaker/latest/dg/deploy-model.html
Key job responsibilities
- Design and implement kernel-level optimizations and inference pipeline improvements that reduce latency and increase throughput for LLM serving workloads.
- Profile, benchmark, and tune model inference performance across hardware and software stacks, identifying bottlenecks and delivering measurable gains.
- Write well-organized, maintainable code and participate actively in code reviews, providing constructive feedback to peers and mentoring newer engineers on the team.
- Collaborate with applied scientists, ML engineers, and infrastructure teams to translate model requirements into production-ready inference solutions.
- Evaluate emerging tools, frameworks, and generative AI techniques for inference optimization, recommending adoption where they improve efficiency or quality.
A day in the life
Here at AWS, we embrace our differences. We are committed to furthering our culture of inclusion. We have ten employee-led affinity groups, reaching 40,000 employees in over 190 chapters globally. We have innovative benefit offerings, and host annual and ongoing learning experiences, including our Conversations on Race and Ethnicity (CORE) and AmazeCon conferences.
About the team
SageMaker Inference team is innovating and modernizing the inference experience that enables the customers to customize their inference workloads. This is an opportunity to establish technical vision, shape product strategy, and build within a proven, high-growth service.
Internal job description
* SageMaker is one of the fastest growing AWS services. You will join the founding team in building an end-to-end ML pipeline platform in SageMaker. It represents a unique opportunity to contribute in developing a new pillar for Amazon's ML platform.
* Applying ML in real-life is still in its early stage and ML practitioners face similar challenges as software engineering teams faced a decade ago. Our mission is to solve challenges in ML like what DevOps solved for software development over the past 10 years. This is a new area in ML with lots of evolvement in concepts, methodology, and solutions.
* We have a deep mix of senior talent presenting itself in Principals and Distinguished Engineers that lead to an extensive level of learning and coaching. This is a great opportunity if you are looking to get into the AI/ML space and want to get hands-on experience building ML platform services at scale.
* Our services are built on native AWS. We embrace modern technologies and server-less/micro-service based architectures, which maximize engineering efficiency and operational excellence.
We own AWS SageMaker (https://w.amazon.com/index.php/AWS/AmazonAI/Platform/IronMan) to empower the world to do more and better Machine Learning.
This is recent launch from team made GA in Q2 2026 (https://docs.aws.amazon.com/sagemaker/latest/dg/realtime-endpoints-heterogeneous.html)
We are looking for internal candidates with prior experience building large scale systems, who are excited about getting into the ML domain.
- 5+ years of non-internship professional software development experience
- 5+ years of programming with at least one software programming language experience
- 5+ years of leading design or architecture (design patterns, reliability and scaling) of new and existing systems experience
- Experience as a mentor, tech lead or leading an engineering team
- 5+ years of full software development life cycle, including coding standards, code reviews, source control management, build processes, testing, and operations experience
- Experience with CUDA kernels or ML/low-level kernels
- Experience with LLM inference and serving optimization, including kernel tuning (CUDA), latency and throughput tuning, profiling and benchmarking, and model execution techniques such as disaggregated serving and KV caching.
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 https://amazon.jobs/content/en/how-we-hire/accommodations for more information. If the country/region you’re applying in isn’t listed, please contact your Recruiting Partner.
The base salary range for this position is listed below. Your Amazon package will include sign-on payments and restricted stock units (RSUs). Final compensation will be determined based on factors including experience, qualifications, and location. Amazon also offers comprehensive benefits including health insurance (medical, dental, vision, prescription, Basic Life & AD&D insurance and option for Supplemental life plans, EAP, Mental Health Support, Medical Advice Line, Flexible Spending Accounts, Adoption and Surrogacy Reimbursement coverage), 401(k) matching, paid time off, and parental leave. Learn more about our benefits at https://amazon.jobs/en/benefits .
USA, WA, Bellevue - 168,100.00 - 227,400.00 USD annually