Software Engineer II - AI/ML, Neuron Inference

Amazon Inc.; Cupertino (CA); On-site; USD 165,000 - 224,000; Full time

Benefits offered by this job

Health insurance

RSUs

401(k) matching

Paid time off

Parental leave

Job summary

Amazon Web Services (AWS) Annapurna Labs team is hiring a Software Engineer II - AI/ML to design and implement features and own model performance on AWS Trainium end to end. You will work across ML frameworks, kernels, and runtimes to optimize inference and enable scale for GenAI workloads.

You'll collaborate with customers to enable and optimize their models on AWS accelerators, build high-performance kernels, and contribute to compiler/runtime improvements across multiple generations of Neuron

Qualifications

• 3+ years of non-internship software development experience.
• 3+ years of design or architecture experience for large systems.
• 1+ years designing and developing large-scale, distributed software applications.
• Bachelor's degree in Computer Science, Engineering, Mathematics, or a related field.
• Experience debugging, profiling, and applying software engineering best practices in large-scale systems.
• Experience with Machine Learning fundamentals, architecture, training/inference lifecycles, and optimization of model execution.
• Knowledge of Python and/or C++ programming.
• Strong understanding of system performance, memory management, and parallel computing principles.

Responsibilities

• Design, develop, and optimize ML models and frameworks for deployment on custom ML hardware accelerators.
• Participate in all stages of the ML system development lifecycle, including distributed computing-based architecture design, implementation, performance profiling, hardware-specific optimizations, testing, and production deployment.
• Build infrastructure to systematically analyze and onboard multiple models with diverse architectures.
• Understand and produce NKI (Neuron Kernel Interface) kernels, and design and implement high-performance kernels and features for ML operations, leveraging the Neuron architecture and programming models.
• Analyze and optimize system-level performance across multiple generations of Neuron hardware, using knowledge of the underlying Trainium hardware architecture to guide optimization decisions.
• Conduct detailed performance analysis using profiling tools to identify and resolve bottlenecks.
• Implement optimizations such as fusion, sharding, tiling, and scheduling.
• Conduct comprehensive testing, including unit and end-to-end model testing with continuous deployment and releases through pipelines.
• Work directly with customers to enable and optimize their ML models on AWS accelerators.
• Collaborate across teams to develop innovative optimization techniques, and share proposals, findings, and learnings with internal developers and external customers via high-quality designs and documentation.

Skills

Software development

Design/architecture

Python programming

C++ programming

Performance optimization

ML fundamentals

Debugging & profiling

Education

Bachelor's degree in Computer Science, Engineering, Mathematics, or related field

Tools

CUDA kernels

TensorRT

PyTorch

JIT compilation

AOT tracing

CUTLASS

SGLang

vLLM

Triton

Job description

The Annapurna Labs team at Amazon Web Services (AWS) builds the AWS Neuron SDK, the software development kit used to accelerate deep learning and GenAI workloads on AWS Trainium machine learning accelerators.

The Neuron Inference organization is at the forefront of optimizing inference performance for a wide range of ML models and model architectures on AWS's custom ML accelerators. We are working across the stack from PyTorch to the hardware-software boundary, our engineers build systematic infrastructure, develop high-performance kernels for ML functions, ensuring every compute unit is fine-tuned for optimal performance forour customers' demanding workloads. We combine deep hardware knowledge with ML expertise to push the boundaries of what's possible in AI acceleration.

As part of the broader Neuron organization, our team works across multiple technology layers — from frameworks and kernels through to compiler, runtime, and collectives. We not only optimize performance on open weight models but also contribute to future architecture designs and work closely with customers to enable optimal performance on their models. This role offers a unique opportunity to work at the intersection of machine learning, high-performance computing, and distributed architectures, where you'll help shape the future of AI acceleration technology.

As a Software Engineer II - AI/ML, you will design and implement business-critical features and own the performance of models on AWS Trainium end to end. We operate in spaces that are very large, yet our teams remain small and agile. There is no blueprint. We're inventing. We're experimenting. It is a very unique learning culture. The team works closely with customers on their model enablement, providing direct support and optimization expertise to ensure their machine learning workloads achieve optimal performance on AWS ML accelerators. The team also collaborates with open source ecosystems to provide seamless integration and bring peak performance at scale for customers and developers.

This role is responsible for development, enablement, and performance tuning of a wide variety of LLM model families, including massive-scale large language models like the GLM, GPT-OSS, Kimi, and beyond. The Model Enablement team works side by side with compiler engineers and runtime engineers to create, build, and tune distributed inference solutions with AWS Trainium.

You can learn more about Neuron:

• https://awsdocs-neuron.readthedocs-hosted.com/en/latest/neuron-guide/neuron-cc/index.html
• https://aws.amazon.com/machine-learning/neuron/
• https://github.com/aws/aws-neuron-sdk
• https://www.amazon.science/how-silicon-innovation-became-the-secret-sauce-behind-awss-success

Key job responsibilities

• Design, develop, and optimize machine learning models and frameworks for deployment on custom ML hardware accelerators.
• Participate in all stages of the ML system development lifecycle, including distributed-computing-based architecture design, implementation, performance profiling, hardware-specific optimizations, testing, and production deployment.
• Build infrastructure to systematically analyze and onboard multiple models with diverse architectures.
• Understand and produce NKI (Neuron Kernel Interface) kernels, and design and implement high-performance kernels and features for ML operations, leveraging the Neuron architecture and programming models.
• Analyze and optimize system-level performance across multiple generations of Neuron hardware, using knowledge of the underlying Trainium hardware architecture to guide optimization decisions.
• Conduct detailed performance analysis using profiling tools to identify and resolve bottlenecks.
• Implement optimizations such as fusion, sharding, tiling, and scheduling.
• Conduct comprehensive testing, including unit and end-to-end model testing with continuous deployment and releases through pipelines.
• Work directly with customers to enable and optimize their ML models on AWS accelerators.
• Collaborate across teams to develop innovative optimization techniques, and share proposals, findings, and learnings with internal developers and external customers via high-quality designs and documentation.

A day in the life

You will collaborate with a cross-functional team of applied scientists, systems engineers, and product managers to deliver state-of-the-art inference capabilities for Generative AI applications. Your work will involve debugging performance issues, optimizing memory usage, and contributing to the future of Neuron's inference stack across Amazon and the Open Source Community. As you design and code solutions to help our team drive efficiencies in software architecture, you'll create metrics, implement automation and other improvements, and resolve the root cause of software defects.

You will also build high-impact solutions to deliver to our large customer base and participate in design discussions and code reviews, and communicate with internal and external stakeholders. You will work cross-functionally to help drive business decisions with your technical input. You will work in a startup-like development environment, where you're always working on the most important initiative.

About the team

The Model Enablement team fosters a builder's culture where experimentation is encouraged and impact is measurable. We emphasize collaboration, technical ownership, and continuous learning. Our team is dedicated to supporting new members. We have a broad mix of experience levels and tenures, and we're building an environment that celebrates knowledge sharing and mentorship. We care about your career growth and strive to assign projects that help our team members develop their engineering expertise so they feel empowered to take on more complex tasks in the future. Join us to solve some of the most interesting and impactful infrastructure challenges in AI/ML today.

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

Los Angeles County applicants: Job duties for this position include: work safely and cooperatively with other employees, supervisors, and staff; adhere to standards of excellence despite stressful conditions; communicate effectively and respectfully with employees, supervisors, and staff to ensure exceptional customer service; and follow all federal, state, and local laws and Company policies. Criminal history may have a direct, adverse, and negative relationship with some of the material job duties of this position. These include the duties and responsibilities listed above, as well as the abilities to adhere to company policies, exercise sound judgment, effectively manage stress and work safely and respectfully with others, exhibit trustworthiness and professionalism, and safeguard business operations and the Company's reputation. Pursuant to the Los Angeles County Fair Chance Ordinance, we will consider for employment qualified applicants with arrest and conviction records.

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.

USA, CA, Cupertino - 165,200.00 - 223,600.00 USD annually

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 .

Basic Qualifications

• 3+ years of non-internship professional software development experience
• 3+ years of non-internship design or architecture (design patterns, reliability and scaling) of new and existing systems experience
• 1+ years of designing and developing large-scale, multi-tiered, multi-threaded, embedded or distributed software applications, tools, systems, and services using: C#, C++, Java, or Perl experience
• Bachelor's degree or foreign equivalent in Computer Science, Engineering, Mathematics, or a related field
• Experience debugging, profiling, and implementing best software engineering practices in large-scale systems
• Experience with Machine Learning and Large Language Model fundamentals, including architecture, training/inference lifecycles, and optimization of model execution
• Knowledge of Python and/or C++ programming
• Strong understanding of system performance, memory management, and parallel computing principles.

Preferred Qualifications

• Experience with CUDA kernels or ML/low-level kernels, or experience in performant kernel development (CUTLASS, FlashInfer)
• Experience with vLLM, SGLang, TensorRT or similar platforms in production environments
• Knowledge of syntax and tile-level semantics similar to Triton
• Knowledge of computer architecture, operating systems, and parallel computing
• Experience with PyTorch, JIT compilation, and AOT tracing
• Knowledge of machine learning model architecture and inference