Software Development Engineer

OverviewThe Annapurna Labs team at AWS builds AWS Neuron, the software development kit used to accelerate deep learning and GenAI workloads on Amazon's custom ML accelerators, Inferentia and Trainium.The AWS Neuron SDK includes an ML compiler, runtime, and application framework that integrates with popular ML frameworks like PyTorch and JAX to enable optimized ML inference and training performance.The Inference Enablement and Acceleration team works across the stack from frameworks to hardware-software boundaries, building infrastructure, innovating methods, and creating high-performance kernels for ML functions to maximize performance on AWS accelerators.The team combines deep hardware knowledge with ML expertise to push the boundaries of AI acceleration and collaborates with customers and open-source ecosystems to enable model enablement and peak performance at scale.As part of the broader Neuron organization, you will architect and implement business-critical features and mentor a team of engineers.We operate in a fast-paced, startup-like culture with no blueprint, where we invent, experiment, and learn.The team collaborates with customers to enable model performance and works with open-source ecosystems for seamless integration.This role is responsible for development, enablement, and performance tuning of a wide variety of LLM model families, including large models like the Llama family.You will work with compiler and runtime engineers to create, build, and tune distributed inference solutions with Trainium and Inferentia, optimizing inference performance across latency and throughput from system level to PyTorch or JAX.Strong Python, system-level programming, and ML knowledge are required.You can learn more about Neuron at the following resources: responsibilitiesThis role will help lead the efforts in building distributed inference support for PyTorch in the Neuron SDK.You will tune these models to ensure high performance on customer AWS Trainium and Inferentia silicon and servers.Strong software development in Python, system-level programming, and ML knowledge are critical.You will collaborate across compiler, runtime, framework, and hardware teams to optimize ML workloads for a global customer base.You will work at the intersection of software, hardware, and ML systems to bring expertise in low-level optimization, system architecture, and ML model acceleration.In this role, you will: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.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.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 CI/CD pipelines.Work directly with customers to enable and optimize their ML models on AWS accelerators.Collaborate across teams to develop innovative optimization techniques.A day in the life – You will collaborate with a cross-functional team of applied scientists, system engineers, and product managers to deliver state-of-the-art inference capabilities for Generative AI applications.You will debug performance issues, optimize memory usage, and shape the future of Neuron's inference stack across Amazon and the Open Source Community.You'll design and code solutions to drive software architecture efficiencies, create metrics, implement automation, and resolve root causes of defects.You will also build high-impact solutions for our large customer base and participate in design discussions, code reviews, and stakeholder communication.You will work cross-functionally to help drive business decisions with technical input in a startup-like development environment.About the teamThe Inference Enablement and Acceleration team fosters a builder's culture with experimentation, impact measurement, collaboration, technical ownership, and continuous learning.We support new members, provide mentorship, and promote knowledge-sharing.We care about career growth and assign projects to develop engineering expertise, empowering team members to take on more complex tasks in the future.Basic Qualifications- 3+ years of non-internship professional software development experience- Bachelor's degree in computer science or equivalent- 3+ years of non-internship design or architecture experience (design patterns, reliability, and scaling) of new and existing systems- Fundamentals of machine learning and LLMs, their architecture, training, and inference lifecycles, with experience optimizing model execution- Software development experience in C++, Python (proficiency in at least one language) and strong understanding of system performance, memory management, and parallel computing principles- Proficiency in debugging, profiling, and implementing best software engineering practices in large-scale systemsPreferred Qualifications- Familiarity with PyTorch, JIT compilation, and AOT tracing- Familiarity with CUDA kernels or equivalent ML/low-level kernels- Experience with performant kernel development (e.g., CUTLASS, FlashInfer) would be beneficial- Familiar with syntax and tile-level semantics similar to Triton- Experience with online/offline inference serving with vLLM, SGLang, TensorRT or similar platforms in production- Deep understanding of computer architecture, OS-level software, and parallel computingEEO and accommodations statements: Amazon is an equal opportunity employer and does not discriminate on the basis of protected veteran status, disability, or other protected status.If you require a workplace accommodation during the application or hiring process, please visit for more information.If your country/region isn't 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 to $223,600/year, depending on factors including location and experience.Amazon is a total compensation company; equity, sign-on, and other benefits may be provided.For more information, visit This position will remain posted until filled.Applicants should apply via our internal or external career site.Posted: January 29, **** (Updated recently)Share this jobImportant FAQs for current Government employees.Before proceeding, please review the following FAQs at