Applied Scientist, WHS Data-Tech

Job summary

DESCRIPTION We're looking for an Applied Scientist to develop computer vision and machine learning models that keep Amazon's workforce safe. Your research and models will be deployed across hundreds of operations facilities globally, helping to reduce safety incidents for over 1.5 million people. You'll join a team where science meets real-world impact.

Benefits

Qualifications

• 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
• PREFERRED
• Experience using Unix/Linux
• Experience in professional software development
• Experience with training and deploying machine learning systems to solve large-scale optimizations, or experience in development or technical support
• Experience with video and image processing and compression algorithms and standards, computer vision and/or machine learning
• PhD, or a PhD or equivalent research experience and experience in patents or publications at top-tier peer-reviewed conferences or journals
• Amazon is an equal opportunity employer and does not discriminate on the basis of protected veteran status, disability, or other legally protected status.

Responsibilities

• You'll join a team where science meets real-world impact.
• You'll design and train models for tasks like activity recognition, anomaly detection, object detection, and risk prediction using video, image, and sensor data from Amazon's operational environments.
• You'll work closely with software engineers to take your models from experimentation through production deployment at scale.
• Design, develop, and deploy computer vision and machine learning models for workplace safety applications (e.g., activity recognition, anomaly detection, pose estimation, object detection)
• Develop and iterate on model architectures using deep learning frameworks, running experiments on large-scale video, image, and sensor datasets
• Collaborate with software engineers to productionize models - optimizing for inference latency, accuracy, and reliability in edge and cloud environments
• Analyze operational data to identify patterns and signals indicating safety risks, and translate findings into actionable model improvements
• Stay current with the latest research in computer vision, deep learning, and related fields, and evaluate applicability to safety use cases
• Communicate findings and technical approaches clearly to both technical and non-technical stakeholders through documents, presentations, and design reviews
• Contribute to the team's scientific culture through code reviews, knowledge sharing, and mentorship
• About the team
• Amazon's Workplace Health & Safety (WHS) organization is responsible for keeping over 1.5 million employees safe across our global retail operations.

Degrees

Industry

Company size