Join the innovative team behind AWS Neuron Compiler, a cutting-edge deep learning compiler stack powering Generative AI and advanced ML workloads on AWS's custom-built ML accelerators — Inferentia and Trainium. As a Machine Learning Compiler Engineer at Annapurna Labs in Tel Aviv, you'll be part of a new core group shaping the future of AI infrastructure.
The role involves working at the intersection of machine learning and systems, focusing on compiler technology and systems-level ML software. You'll be tackling complex challenges in compiler optimization, graph theory, and hardware-software integration. The position offers unique opportunities to work with AWS's custom ML accelerators that deliver industry-leading performance and cost-efficiency for ML inference and training in the cloud.
Your responsibilities will span across multiple technical domains, from instruction scheduling and memory management to ISA design and hardware bring-up. You'll collaborate with cross-functional teams including Runtime, Frameworks, and Hardware to optimize end-to-end performance. The role requires strong programming skills in C++ or Python, along with deep understanding of compiler design, parallel programming, and machine learning frameworks.
This is an exceptional opportunity to work in a startup-like environment within AWS, where you'll have direct impact on global customers while building next-generation AI infrastructure. The position offers the stability and resources of Amazon while maintaining the innovation speed of a startup. You'll be part of AWS's Utility Computing organization, working alongside teams responsible for foundational services like S3 and EC2.
The role combines technical depth with broad impact, requiring both specialized knowledge in compiler technology and the ability to work across different layers of the technology stack. If you're passionate about pushing the boundaries of ML infrastructure and want to be at the forefront of AI innovation, this role offers the perfect platform to make a significant impact in the field.