Data Scientist

JOB DESCRIPTION: Perform statistical analysis of a/b tests and build machine learning ranking models for search result ranking and personalized recommendations. Build models for category classifiers in predicting categories for a product or search keyword, fine tune out of box models such as word2vec or Bert, text embedding, customer segmentations models, and help support various business decision making process. Complete ownership from requirements, solution design, development, production launch and post launch production support. Work through all phases of development including data analysis, model prototyping, model evaluation (offline/online), training data set, automation and maintenance. Participate in code reviews and regular on-call rotations. Collaborate with other teams including search and data engineering, web and marketing analysts, data analyst, project managers, system team and other contractors/consultants. Write code in Python/R using various statistical techniques and

machine learning models, maintain all the code in repository such as Git/Bitbucket. Hands on development and deliver the work in sprint cycle. Develop visualization of data with tools such as Jupyter notebooks and integrations with Tableau. A/B test evaluation, share the findings with the team. Communicate summarized results to technical and non-technical stakeholders to help them make decision. Work with search engineers and data engineers in integrating ML models, analytics pipeline, work with ML Engineers/Data Engineers in deploying models to production, participate in MLOps processes. Work with stakeholders throughout the organization to identify opportunities for leveraging machine learning techniques across other business verticals. Mentor Jr. team members, define architecture, code review.

REQUIREMENTS: Must possess a Bachelor’s degree in Computer Science, Business Analytics, or a closely related degree and 5 years of experience in the job offered or related role. Must possess experience with: (i) Machine learning Tech Stack; (ii) PyTorch; (iii) TensorFlow; (iv) Scikit-learn; (v) Pandas; (vi) Python R; (vii) Deep Learning frameworks; (viii) Database SQL queries; (ix) AWS Athena; (x) BigQuery and Google Analytics tagging and integration; (xi) ML models for information retrieval algorithms; (xii) Transformers and encoders; (xiii) ANN/KNN; and (xiv) Programming skills, statistical techniques, clustering techniques, predictive modeling, AI/ML/NLP, architecture diagramming, and problem solving and debugging skills.