Applied Scientist, Neuron ARG

The AWS Neuron Compiler team is seeking applied scientists to develop a state-of-the-art deep learning compiler stack. This role involves optimizing application models across diverse domains, including Large Language and Vision, from frameworks like PyTorch, TensorFlow, and JAX. You'll work with custom-built Machine Learning accelerators like Inferentia/Trainium, powering advanced ML capabilities and Generative AI solutions.

As an Applied Scientist in the Automated Reasoning Group, you'll:

• Design, develop, and deploy analyzers for ML compiler stages and compiler IRs
• Contribute to the design and semantics of DSLs for neural architectures
• Architect and implement business-critical tooling
• Publish cutting-edge research
• Mentor a team of experienced scientists and engineers
• Tackle crucial challenges in compiler technology and deep-learning systems software

Required qualifications:

• PhD
• Experience programming in Java, C++, Python or related language
• Experience with neural deep learning methods and machine learning

Preferred qualifications:

• 3+ years of applied research experience
• Experience with LLVM or similar frameworks
• Knowledge of abstract interpretation
• Familiarity with SMT or decision procedures
• Experience in program synthesis

The role offers flexibility with options to work in the office daily or in a hybrid model near one of Amazon's U.S. offices. Amazon values diversity, inclusion, and work-life harmony, providing various employee-led affinity groups, mentorship opportunities, and career development resources.

Base pay range: $150,400/year to $260,000/year, depending on geographic market and other factors. Total compensation may include equity, sign-on payments, and a full range of benefits.