Full Job Description
We're looking for an experienced Senior Software Development Engineer to help build and scale the distributed inference engine that powers Amazon Bedrock. As part of the AWS Mantle team, you will design and deliver critical systems that enable millions of customers to access the world's leading foundation models-securely, reliably, and at global scale. This is an opportunity to work on one of the most impactful AI infrastructure platforms at AWS, where your code and design decisions will directly shape how generative AI is served to enterprises worldwide.
Design, build, and operate high-performance distributed systems that serve ML inference at massive scale across all AWS regions
Own the end-to-end delivery of complex features-from requirements through design, implementation, testing, deployment, and production operations
Collaborate with cross-functional teams to solve challenging problems in capacity management, model serving, and API compatibility
Contribute to a culture of engineering excellence by writing clean, maintainable code and driving continuous improvement in system reliability
Influence technical direction within your team while contributing to broader architectural discussions across Mantle and Amazon Bedrock
Key job responsibilities
As a Senior SDE on the Mantle team, you will be a hands-on technical leader who owns significant components of our inference platform. You will balance deep technical execution with thoughtful design, delivering solutions that are scalable, secure, and operationally excellent-while mentoring teammates and raising the bar for the team.
Design and implement core components of Mantle's distributed inference engine, including request routing, load balancing, model lifecycle management, and quality-of-service enforcement
Build and operate services that onboard new foundation models rapidly while maintaining strict performance SLAs and Zero Operator Access (ZOA) security guarantees
Drive operational excellence by owning your team's services in production-monitoring, alarming, incident response, and continuous reliability improvement
Partner with applied scientists, ML engineers, and partner teams to integrate new model architectures and optimize inference performance across GPU/accelerator fleet.
Mentor junior and mid-level engineers through code reviews, design reviews, and hands-on guidance that elevates the team's technical capabilities
BASIC QUALIFICATIONS
- 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
- Bachelor's degree in Computer Science, Engineering, a related field, or equivalent experience
PREFERRED QUALIFICATIONS
- Master's degree in computer science, machine learning, engineering, or related fields
- Experience in machine learning, data mining, information retrieval, statistics or natural language processing, or experience in developing and deploying LLMs in production on GPUs, Neuron, TPU or other AI acceleration hardware
- Experience designing APIs at scale, particularly RESTful or streaming APIs with strict latency and availability requirements
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, Seattle - 168,100.00 - 227,400.00 USD annually