Engineer and iterate on features from underlying data, combining domain understanding with statistical rigor to propose, evaluate, and refine feature sets that improve model performance over successive cycles. Run regular A/B tests, gather data, perform statistical analysis, draw conclusions on the impact of your optimizations and communicate results to peers and leaders.
Numbers & Facts
Location
Santa Clara, CA
Description
Indent: SF_OP_211893-4/ SF_OP_211893-3
Role: Data Scientist
Location: Oakland/MTV/San Diego CA (3 days Work from Office)
Max Rate: $65/hr
Responsibilities
Perform hands-on data analysis and modeling with huge data sets
Apply data mining, NLP, and supervised/unsupervised ML to design, improve, and evaluate relevance and personalization algorithms across customer journeys.
Work side-by-side with product managers, software engineers, and designers in designing experiments and minimum viable products
Client data sources, get access to them, import them, clean them up, and make them "model-ready”. You need to be willing and able to do your own ETL
Engineer and iterate on features from underlying data, combining domain understanding with statistical rigor to propose, evaluate, and refine feature sets that improve model performance over successive cycles.
Run regular A/B tests, gather data, perform statistical analysis, draw conclusions on the impact of your optimizations and communicate results to peers and leaders
Explore new design or technology shifts in order to determine how they might connect with the customer benefits we wish to deliver
Qualifications:
BS, MS, or PhD in an appropriate technology field (Computer Science, Statistics, Applied Math, Operations Research, etc.)
4+ years of industry experience with Data Science and Machine Learning
4+ years of experience in modern advanced analytical tools, programming languages - Python with scikit-learn
Efficient in SQL, Hive, SparkSQL, etc.
4+ years of experience in applied machine learning and statistical modeling (e.g., classification, regression, decision trees, neural networks, recommender systems, sequential pattern discovery, and text mining), with hands-on experience in deep learning and embedding-based representations for NLP/language understanding, recommendation, and personalization.
Solid communication skills: Demonstrated ability to explain complex technical issues to both technical and non-technical audiences