POSTED Nov 25
Applied Scientist II, Decision Science and Technology (DST)
at Amazon ⋅ US, WA, Bellevue
We are looking for talented Applied Scientists who are adept at a variety of skills, especially with LLMs, use of edge devices, computer vision, or related foundational models that will accelerate our plans to generate high-quality defect detection mechanisms.
Our mission is to improve the reliability of equipment (conveyors, motors, belts), and effectively identify from sensors, images, and video specific actions on material handling equipment (MHE) that can prevent unplanned downtime. With millions of products available on Amazon.com comes variation in weight, size, material, and shape. We build products and systems to detect and prevent equipment downtime using a diverse set of classification and anomaly detection algorithms including LLMs. We screen over 150 million events every day, and process this data to create real time alerting systems. We are still day 1 and have an exciting roadmap to build AI predictive maintenance models, deploy scalable causal inference solutions to measure the impact of events, and optimize the reliability of conveyance helping Amazon scale for years to come.
As an Applied Scientist II, you will design, develop, and maintain scalable, Artificial Intelligence models with automated training, validation, monitoring and reporting. You will work closely with other scientists and engineers to architect and develop new learning algorithms and prediction techniques. You will collaborate with product managers and engineering teams to design and implement scientific solutions for Amazon problems. Provide technical and scientific guidance to your team members. Contribute to the research community, by working with other scientists across Amazon and publish papers at peer reviewed journals and conferences.
Key job responsibilities
- Design and implement scalable infrastructure that enables stacked deep learning models to detect a variety of defects in fractions of a second;
- Design and implement anomaly detection and large language models to identify defects associated with customer packages;
- Experiment and scale models to thousands of sites worldwide;
- Collaborate with RME internal and external stakeholders and have a cross-team impact;
- Create and share with audiences of varying levels technical papers and presentation.
About the team
We are a growing team of applied, research, and data scientists working together with an engineering team and product managers to create the next-generation IIoT platform for the Reliability and Maintenance Engineering org.
Our mission is to improve the reliability of equipment (conveyors, motors, belts), and effectively identify from sensors, images, and video specific actions on material handling equipment (MHE) that can prevent unplanned downtime. With millions of products available on Amazon.com comes variation in weight, size, material, and shape. We build products and systems to detect and prevent equipment downtime using a diverse set of classification and anomaly detection algorithms including LLMs. We screen over 150 million events every day, and process this data to create real time alerting systems. We are still day 1 and have an exciting roadmap to build AI predictive maintenance models, deploy scalable causal inference solutions to measure the impact of events, and optimize the reliability of conveyance helping Amazon scale for years to come.
As an Applied Scientist II, you will design, develop, and maintain scalable, Artificial Intelligence models with automated training, validation, monitoring and reporting. You will work closely with other scientists and engineers to architect and develop new learning algorithms and prediction techniques. You will collaborate with product managers and engineering teams to design and implement scientific solutions for Amazon problems. Provide technical and scientific guidance to your team members. Contribute to the research community, by working with other scientists across Amazon and publish papers at peer reviewed journals and conferences.
Key job responsibilities
- Design and implement scalable infrastructure that enables stacked deep learning models to detect a variety of defects in fractions of a second;
- Design and implement anomaly detection and large language models to identify defects associated with customer packages;
- Experiment and scale models to thousands of sites worldwide;
- Collaborate with RME internal and external stakeholders and have a cross-team impact;
- Create and share with audiences of varying levels technical papers and presentation.
About the team
We are a growing team of applied, research, and data scientists working together with an engineering team and product managers to create the next-generation IIoT platform for the Reliability and Maintenance Engineering org.
Related Jobs
Meta
Research Scientist Intern, Graph Science and Statistics Research (PhD)
Menlo Park, CA, New York, NY