As a data scientist on the SOI team, you will primarily develop machine learning solutions that will predict a customers needs/intentions in real-time at the moment of interaction, in batch prior to the event, or in batch after the event for analytical labeling/categorization. The outputs of these models will then be used to determine the optimal engagement and experience to provide to the customer.
Job Duties:
- You will partner with functional and channel stakeholders to define use cases and model targets. You will work with domain experts to understand data sources and complete feature engineering.
- You will design and execute experiments with training data sets to determine the best models to apply and perform cross validation to test the efficiency of the resulting algorithms.
- When algorithms reach adequate efficiency thresholds, you will partner with production engineers to deploy your models for run-time scoring. You will compare the live performance of your models to expectations and evaluate any gaps.
- In addition to model development, you may, independently or within a team, need to build solutions to support the overall project, including label generation, data schemas, ad hoc analytics, output structure/packaging, or end-to-end prototype demos.
- You will be responsible for presenting your own work to team members, peers, and leadership, and will build any visualizations or presentations necessary for those communications.
Must Have skills:
- Knowledge of predictive/prescriptive analytics including Machine Learning algorithms (Supervised and Unsupervised), Artificial Neural Networks (CUDA, Keras, Tensorflow) or Combinatorics (Mixed Integer Programming).
- Experience leading the end-to-end design, development, and deployment of predictive modeling solutions.
- Advanced SQL skills with Teradata, SQL Server, Hive and Spark experience.
- Experience with scripting languages such as Python/R or compiling languages such as C/C++ or Java.
- Proficiency iLinux Shell/equivalent, and familiarity with HDFS.
- Familiarity with Git (Bash or command line).
- Experience with Natural Language Processing (NLTK) and text analytics for information extraction, parsing and topic modeling.
- Experience automating data within Tableau/Qlik/ggplot/Shiny to tell an analytical story through interactive visualizations.
- Experience and knowledge of NLP including NER and text summarization.
- Experience and knowledge of deep neural networks, including CNN and RNN.
- Experience with text parsing/regular expressions.
Desired Skills:
- Six or more years of relevant work experience
- Ability to plan work and meet deadlines
- Accuracy and attention to detail
- Experience with using big data to develop models.
- Experience with Spark.
- Strong problem solving, analytical, and research capabilities.
- Strong verbal and written communication
- Experience presenting to and influencing functional leaders and stakeholders.
- Deep expertise in applying machine learning to solve a class of AI problems such as NLU/NLP, Reinforcement Learning, Voice Biometrics, Text Mining, and Intelligent Process Automation.
Qualification:
- Masters or Doctorate in Computer Science, Artificial Intelligence, Business Analytics, Operations Research, Engineering or Statistics.
Didn’t find the job appropriate? Report this Job