Applied Scientist, Computer Vision for Workplace Safety

Amazon; San Francisco, Northern (CA, KY); Hybrid; USD 140,000 - 190,000; Full time

Benefits offered by this job

RSUs

Sign-on bonus

Comprehensive benefits

Job summary

Amazon in San Francisco is seeking an Applied Scientist to develop computer vision and ML models for workplace safety. You will deploy models across global facilities, optimizing for latency and accuracy in edge and cloud environments.

You will collaborate with software engineers and safety experts to translate research into scalable production systems that reduce injuries and improve operational safety at scale.

Qualifications

• 3+ years of building models for business applications.
• PhD or Master’s in CS/CE/ML with 4+ years of related experience.
• Experience with patents or publications in top venues.
• Proficient in Java, C++, Python.
• Experience in algorithms, data structures, optimization, data mining, parallel and distributed computing, HPC.

Responsibilities

• Design, develop, and deploy CV/ML models for workplace safety.
• Iterate on model architectures using large video, image, and sensor data.
• Collaborate with software engineers to productionize models for edge and cloud.
• Analyze operational data to improve safety-related signals.
• Stay current with CV, DL research and apply to safety use cases.
• Communicate findings to technical and non-technical stakeholders.
• Contribute to scientific culture via code reviews and mentorship.

Skills

Model development

Python

Java/C++

Deep learning

ML fundamentals

Education

Master’s or PhD in CS/CE/ML

Tools

Unix/Linux

Job description

Amazon in San Francisco is seeking an Applied Scientist to develop computer vision and ML models for workplace safety. You will deploy models across global facilities, optimizing for latency and accuracy in edge and cloud environments.

You will collaborate with software engineers and safety experts to translate research into scalable production systems that reduce injuries and improve operational safety at scale.