Software Development Engineer I, Inference models optimization, AWS Neuron Inference

About the role

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 for our 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 I, you will design and implement business-critical features and contribute to optimizing 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 GLM, 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: If this sounds exciting to you - come build the future with us!

Key job responsibilities

• Optimize open models to run best on Trainium, including optimizing sharding, developing NKI kernels and ensuring accuracy. This provides ready-to-serve models to our customers and also gives them a starting point to optimize their own.
• Collaborate with cross-disciplinary teams that may include hardware design, firmware, compiler, runtime, and ML engineers to develop software that enables and optimizes custom ML accelerator silicon
• Write clean, maintainable code (C/C++, Python, or Rust) following best practices for systems-level and performance-critical development
• Participate in code reviews, contribute to technical documentation, and help deploy agentic tools to accelerate the enablement of new models on Trainium
• Demonstrate operational excellence through monitoring, debugging, and resolving issues across hardware-software integration boundaries, including on-call responsibilities
• Keep learning emerging technologies in ML accelerators, compiler optimization, computer architecture, and cloud-scale distributed systems

Basic Qualifications

• Experience with data structure implementation, basic algorithm development, and/or object-oriented design principles
• Currently has, or is in the process of obtaining, a Bachelor's degree or above in Computer Science, Computer Engineering, Electrical Engineering, or related fields
• Experience with any programming language such as Python, Java, C++

Preferred Qualifications

• Experience from previous technical internship(s) or demonstrated project experience
• Experience with one or more of the following: compiler design or optimization, computer architecture, hardware simulation or emulation, ML frameworks (PyTorch, JAX), performance profiling and analysis, Linux kernel or embedded systems, AI tools for development productivity, cloud platforms (preferably AWS), version control systems
• Strong problem-solving skills with ability to debug across hardware-software boundaries
• Demonstrated ability to learn and adapt to new technologies quickly

Additional information

Our inclusive culture empowers Amazonians to deliver the best results for our customers. If the country/region you're applying in isn't listed, please contact your Recruiting Partner.

Pay and benefits

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.

USA, CA, Cupertino - 127,100.00 - 185,000.00 USD annually