AWS Neuron is seeking a senior software engineer for their Compiler team to help revolutionize AI development. This role focuses on building the next generation Neuron compiler that transforms ML models from frameworks like PyTorch, TensorFlow, and JAX for deployment on AWS Inferentia and Trainium servers. The position involves solving complex compiler optimization challenges for various ML model families, including large language models, stable diffusion, and vision transformers.
The role combines deep technical expertise with collaborative teamwork, requiring interaction with chip architects, runtime engineers, and ML teams. You'll be instrumental in optimizing performance for cutting-edge ML models and working with open-source communities to influence industry standards. The position offers opportunities to work on pre-silicon design and bring new products to market.
As part of AWS's Machine Learning team, you'll contribute to democratizing access to cutting-edge AI infrastructure. The team values knowledge-sharing, mentorship, and career growth, fostering an environment where engineers can develop their expertise through challenging projects and supportive code reviews.
AWS offers comprehensive benefits, emphasizes work-life harmony, and provides ongoing learning opportunities. The company values diverse experiences and backgrounds, maintaining an inclusive culture through employee-led affinity groups and regular diversity-focused events. This position represents an opportunity to shape the future of machine learning infrastructure while working with industry-leading technology at scale.
The role requires strong programming skills in object-oriented languages, with compiler experience preferred. Knowledge of ML frameworks and accelerators is valuable, as is familiarity with OpenSource compiler toolsets like LLVM/MLIR. The position offers competitive compensation based on location and experience, along with equity opportunities and comprehensive benefits.