Applied Scientist II: Multimodal NLP for Search at Scale

Amazon; Seattle (WA); On-site; USD 143,000 - 193,000; Full time

Job summary

Amazon seeks an Applied Scientist II for Natural Language and Multimodal Search in Seattle. You will design and deploy deep-learning models that combine text and product images to improve search relevance and ranking for constrained shopping queries.

Expect cross-team collaboration, experimentation, and production-scale impact across millions of customer queries. Responsibilities include building data pipelines, training encoders, and running offline/online experiments.

Qualifications

• PhD, or Master's degree and 2+ years of CS, CE, ML or related field experience
• Experience programming in Java, C++, Python or related language
• Experience with ML, RL, DL, CV or NLP related applications

Responsibilities

• Design, train, and ship deep-learning ranking and semantic-matching models over text and images
• Build training data and evaluation methods including hard-negative mining
• Train and adapt vision-language encoders for multimodal relevance signals
• Create joint text and image embeddings for retrieval and ranking
• Run offline and online A/B experiments and iterate to improve relevance

Skills

Java

C++

Python

Machine Learning

NLP

Deep Learning

Computer Vision

Education

Masters or PhD in CS/CE/ML or related field

Job description

Amazon seeks an Applied Scientist II for Natural Language and Multimodal Search in Seattle. You will design and deploy deep-learning models that combine text and product images to improve search relevance and ranking for constrained shopping queries.

Expect cross-team collaboration, experimentation, and production-scale impact across millions of customer queries. Responsibilities include building data pipelines, training encoders, and running offline/online experiments.