DESCRIPTION

Alexa is Amazon's intelligent cloud-based voice recognition and natural language understanding virtual assistant. We're building the speech and language solutions behind Amazon Alexa and other Amazon products and services. Come join our team and help improve the customer experience for the growing base of Alexa users!

As an Applied Scientist in our Natural Understanding Central Analytics & Research Science team (part of Alexa AI), you will work on assessing Alexa's performance using predictive ML models. You will build and improve models to classify Alexa's responses as correct/incorrect, and predict the most likely cause of failure in cases of incorrect action. Your work will directly impact our customers in the form of products and services that make use of speech and language technology, particularly in developing predictive models to continuously improve the Alexa experience for our customers.

You will:
• Design, build, test and release predictive ML models
• Ensure data quality throughout all stages of acquisition and processing, including such areas as data sourcing/collection, ground truth generation, normalization, and transformation.
• Collaborate with colleagues from science, engineering and business backgrounds.
• Present proposals and results to partner teams in a clear manner backed by data and coupled with actionable conclusions
• Work with engineers to develop efficient data querying and inference infrastructure for both offline and online use cases

BASIC QUALIFICATIONS

• Hands on experience with classical ML models (e.g., regression, trees), test/train/evaluation metrics, key parameters/techniques that affect model performance
• Familiarity and ideally experience with more recent deep ML models (e.g., Transformers, BERT).
• Experience with Python/PySpark; solid knowledge SQL.
• Experience analyzing data to identify patterns and conducting error/deviation analysis; passion for fixing issues in the data and finding the optimal representation.
• A business analytical mind; ability to communicate with consumers of the model and present results in intuitive ways.
• Understanding of relevant statistical measures such as confidence intervals, significance of error measurements, development and evaluation data sets.

PREFERRED QUALIFICATIONS

• PhD in a relevant field (Computer Science, Computer or Electrical Engineering, Mathematics, Physics, Statistics or a related field)
• Experience diving into data to discover hidden patterns and of conducting error/deviation analysis
• Ability to develop experimental and analytic plans for data modeling processes, use of strong baselines, ability to accurately determine cause and effect relations
• Strong attention to detail and exceptional level of organization
• Proven ability to achieve results in a fast paced, highly collaborative, dynamic work environment
• Ability to think creatively and solve problems
Amazon.com is an Equal Opportunity-Affirmative Action Employer - Minority / Women / Disability / Veteran / Gender Identity / Sexual Orientation