Do you want to revolutionize machine learning for edge devices? Join our team developing cutting-edge compression algorithms that enable AI models to run efficiently on resource-constrained hardware. Our work is transforming the way Amazon customers interact with our devices, creating novel experiences that push the boundaries of what's possible with AI.
About the role:

As an Applied Scientist on the Edge AI & ML team, you will be at the forefront of innovation, working on technology that directly impacts millions of Amazon customers. Our team is pioneering new approaches that achieve an order of magnitude higher compression rates compared to existing methods. You'll work on challenging problems at the intersection of deep learning, optimization, and systems.
By optimizing ML models for edge deployment, we're bringing advanced AI closer to our customers, enhancing privacy, reducing latency, and enabling new features that were previously impossible.

Your work will:

- Power the next generation of Amazon devices with efficient, on-device AI
- Enable novel customer experiences that respond in real-time, even without internet connectivity
- Push the boundaries of what's possible with edge computing and machine learning

Key job responsibilities
As an Applied Scientist on the Edge AI ML team, you will:

- Develop and implement novel algorithms for compressing and optimizing deep learning models for edge devices
- Conduct experiments to evaluate and benchmark model performance across various hardware platforms
- Collaborate with product teams to integrate our technology into Amazon devices and services
- Innovate on techniques to achieve state-of-the-art efficiency in AI model deployment
- Explore and adapt emerging ML architectures (e.g., transformers, neural architecture search) for edge computing
- Investigate hardware-aware ML techniques to tailor models for specific edge devices


About the team
Our team is at the forefront of enabling AI capabilities on edge devices. We offer:

- The opportunity to work on cutting-edge ML technologies with real-world impact
- Collaboration with world-class researchers and engineers
- A culture of innovation that encourages new ideas and approaches
- The scale and resources of Amazon to tackle ambitious technical challenges- 3+ years of building models for business application experience
- PhD, or Master's degree and 4+ years of CS, CE, ML or related field experience
- Experience in patents or publications at top-tier peer-reviewed conferences or journals
- Experience programming in Java, C++, Python or related language
- Experience in any of the following areas: algorithms and data structures, parsing, numerical optimization, data mining, parallel and distributed computing, high-performance computing
- Strong programming skills in Python and experience with deep learning frameworks like PyTorch or TensorFlow- Experience using Unix/Linux
- Experience in professional software development
- Experience with model compression techniques like pruning, quantization, and knowledge distillation
- Familiarity with deploying ML models on edge devices or mobile platforms
- Background in optimization, information theory, or signal processing
- Track record of developing novel ML algorithms and seeing them through to practical implementation
- Publication record in top-tier ML conferences (e.g. NeurIPS, ICML, ICLR)

Amazon is committed to a diverse and inclusive workplace. Amazon is an equal opportunity employer and does not discriminate on the basis of race, national origin, gender, gender identity, sexual orientation, disability, age, or other legally protected status. If you would like to request an accommodation, please notify your Recruiter.

The base salary for this position ranges from $149,300/year up to $249,300/year. Salary is based on a number of factors and may vary depending on job-related knowledge, skills, and experience. Amazon is a total compensation company. Dependent on the position offered, equity, sign-on payments, and other forms of compensation may be provided as part of a total compensation package, in addition to a full range of medical, financial, and/or other benefits. Applicants should apply via our internal or external career site.