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

Senior Software Development Engineer – AI/ML, AWS Neuron, Multimodal Inference

Posted 2 day ago. Be among the first 25 applicants.

The Annapurna Labs team at 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 these 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.

The Inference Enablement and Acceleration team works at the forefront of running a wide range of models and supporting novel architectures while maximizing performance on AWS’s custom ML accelerators. Working across the stack from PyTorch to the hardware‑software boundary, our engineers build systematic infrastructure, innovate new methods, and create 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, the team works across multiple technology layers—from frameworks and kernels and collaborating with compiler to runtime—to optimize current performance and contribute to future architecture designs. The 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.

• 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.

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. Your work will involve debugging performance issues, optimizing memory usage, and shaping the future of Neuron’s inference stack across Amazon and the open source community. You’ll build high‑impact solutions, participate in design discussions, code reviews, and communicate with internal and external stakeholders in a startup‑like environment.

The Inference Enablement and Acceleration team fosters a builder’s culture where experimentation is encouraged. Collaboration, technical ownership, and continuous learning are valued. Our senior members provide one‑on‑one mentoring and thorough, but kind, code reviews.

• 5+ years of non‑internship professional software development experience.
• Bachelor’s degree or equivalent in Computer Science.
• 5+ years of non‑internship design or architecture (design patterns, reliability and scaling) of new and existing systems experience.
• Fundamentals of Machine learning and LLMs, their architecture, training and inference life cycles along with experience on optimizations for improving model execution.
• So…