Senior Software Development Engineer, AI​/ML, AWS Neuron, Model Inference

Overview

The Annapurna Labs team at Amazon Web Services (AWS) builds AWS Neuron, the software development kit used to accelerate deep learning and GenAI workloads on Amazon’s custom machine learning accelerators, Inferentia and Trainium. The Neuron SDK is the backbone for accelerating deep learning and GenAI workloads on Amazon’s Inferentia and Trainium ML accelerators. It includes an ML compiler, runtime, and application framework that seamlessly integrates with popular ML frameworks like PyTorch and JAX, enabling unparalleled ML inference and training performance.

Design and implement business‑critical features for distributed inference support for PyTorch in the Neuron SDK, optimizing models to ensure highest performance on AWS Trainium and Inferentia servers. Lead a small, agile team of experienced engineers and collaborate across compiler, runtime, framework, and hardware teams to optimize machine learning workloads for our global customer base.

• 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 architecture.
• 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 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.

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. Debug performance issues, optimize memory usage, shape the future of Neuron’s inference stack across Amazon and the Open Source Community, create metrics, implement automation, resolve software defects, and build high‑impact solutions for a large customer base.

The Inference Enablement and Acceleration team fosters a builder’s culture where experimentation is encouraged, and impact is measurable. We emphasize collaboration, technical ownership, and continuous learning, and provide mentorship and growth opportunities for all team members.

• Bachelor’s degree in computer science or equivalent.
• 5+ years of professional software development experience (non‑internship).
• 5+ years of design or architecture experience for new and existing systems, focusing on reliability and scaling.
• Fundamentals of machine learning and LLMs, their architecture, training and inference life cycles, and experience with optimizations to improve model execution.
• Software development experience in C++ and Python (experience in at least one language is required).
• Strong understanding of system performance, memory management, and parallel computing principles.
• Proficiency in debugging, profiling, and implementing best software engineering practices in large‑scale systems.

• Master’s degree in computer science or equivalent.
• 5+ years of full software development life cycle experience, including coding standards, code reviews, source control management, build processes, testing, and operations.
• Familiarity with PyTorch, JIT compilation, and AOT tracing.
• Familiarity with CUDA kernels or equivalent ML or low‑level kernels; experience with performant kernel development such as CUTLASS, Flash Infer.
• Familiar with syntax and tile‑level semantics similar to Triton.
• Experience with online/offline…