An exciting opportunity has opened up on my team at Amazon. We're seeking a Senior Applied Scientist to join the Selling Partner Communities (SPC) Science team and lead our multi-year voice of seller Machine Learning projects. This hands-on, pivotal role will take research to production, leveraging NLP, sentiment analysis, LLMs, RAGs, and causal modeling. The job location could be in Seattle, San Diego, or Arlington, in a hybrid work from home and office setting. In this position, you'll collaborate closely with senior leadership to identify high-impact opportunities based on diverse user feedback and develop novel ML approaches to address them. This includes designing and deploying sophisticated NLP models, building scalable data pipelines, and integrating cutting-edge ML-based solutions to directly support Amazon's vast network of selling partners. Key responsibilities: Partner cross-functionally to define requirements, set success metrics, and deliver impactful ML solutions Extract insights from advanced techniques like sentiment analysis, named entity recognition, and time series analysis to inform product enhancements Continuously research and evaluate new ML/NLP approaches to enhance current solutions Work closely with data/software engineers to seamlessly integrate successful models into production systems Publish at top-tier research conferences and mentor junior scientists, providing feedback on their work

The application of neuroimaging methods to marketing has recently gained lots of attention. In analyzing consumer behaviors, the inclusion of neuroimaging tools and methods is improving our understanding of consumer’s preferences. Human emotions play a significant role in decision making and critical thinking. Emotion classification using EEG data and machine learning techniques has been on the rise in the recent past. We evaluate different feature extraction techniques, feature selection techniques and propose the optimal set of features and electrodes for emotion recognition.Affective neuroscience research can help in detecting emotions when a consumer responds to an advertisement. Successful emotional elicitation is a verification of the effectiveness of an advertisement. EEG provides a cost effective alternative to measure advertisement effectiveness while eliminating several drawbacks of the existing market research tools which depend on self-reporting. We used Graph theoretical principles to differentiate brain connectivity graphs when a consumer likes a logo versus a consumer disliking a logo. The fusion of EEG and sentiment analysis can be a real game changer and this combination has the power and potential to provide innovative tools for market research.