Amazon Task Jobs in Perth Amboy, NJ (NOW HIRING)

Do you want to join a brand-new team building an AI system that would disrupt the industry. Do you enjoy dealing with ambiguity and working on hard problems in a fast-paced environment?
Amazon Connect is a highly disruptive cloud-based contact center that enables businesses to deliver engaging, dynamic, and personal customer service experiences. With Amazon Connect, you can create your own cloud-based contact center and be taking calls in minutes.

Amazon Connect leverages the power of Artificial Intelligence and the large ecosystem of AWS services such as Lex, Polly, Lambda, S3, and Kinesis to provide a truly frustration free and natural customer experience. With this technology, we are transforming an industry and the way customers interact with businesses and how agents service them.
As a Data Scientist on our team, you will analyze data from massive data sets to categorize customer idiosyncrasies, identify outliers, and systematically detect anomalies that substantially affect the performance of our models.

You will work closely with other senior technical leaders within the team and across AWS. You should know how to trace decisions in data from raw data through complex models to their impact business metrics. Experience with machine learning explainability is a plus.

You should be able to translate well-defined business problems into data science problems and you solve these problems using appropriate assumptions, methodologies, and data science best practices. Our team is at an early stage, so you will have significant impact on our deliverables with no operational load from existing models/systems.
We have a rapidly growing customer base and an exciting charter in front of us that includes solving highly complex engineering and algorithmic problems. We are looking for passionate, talented, and experienced people to join us to innovate on this new service that addresses customer needs to build modern contact centers in the cloud

The position represents a rare opportunity to be a part of a fast-growing business soon after launch, and help shape the technology and product as we grow. You will be playing a crucial role in developing the next generation contact center, and get the opportunity to design and deliver scalable, resilient systems while maintaining a constant customer focus.
Learn more about Amazon Connect here:
https://aws.amazon.com/connect/
Key job responsibilities
Categorizing Customer Idiosyncrasies: As we expand to more customers, we are discovering that they use our product in very different ways and that poses issues for our models

Effectively summarizing these differences (for example, X% of customers do Y) would be immensely helpful.
Detecting and Cleaning Up Outliers: We have situations where outliers have a huge impact on model outputs. You will help us develop mechanisms to clean up outliers for downstream consumption.
Deep Diving Customer Issues: Customers have longstanding traditions and trusted formulas for managing their contact centers. When our formulas differ from theirs, we need to deep dive these discrepancies and determine if there is an issue with our model or if we are giving the customer better results than they are used to.
Assessing Data Gaps: It's hard to estimate the weather in Seattle if the only data you have is the average weight of elephants in Zimbabwe

We know we don't have all the data we need, but we need to answer two related questions: (a) what features can we derive in creative ways from existing data sources. (b) can we estimate the benefit of getting a new data stream in terms of accuracy improvement?
A day in the life
Our team uses agile project management, so the DS calls in to our daily stand-up meeting in the morning to report status and explain their tasks for the day. Throughout the day, the DS will work with our product manager to discuss issues with our customers that require deep dives, work with our scientists to discuss model performance issues, and discuss software deliverables with our SDEs such as automation of data ingestion to save DS time, deployment of models, etc.