Possesses a wide variety of deep technical skills, focused on highly stable, highly available server side development, including large-scale data processing pipelines with Hadoop and machine learning algorithms. Experience working with and contributing to open source projects, including Hive
.
Complementing these skills, the applicant also has core capabilities in rich web application / browser environments, architecture and deployment. Well versed in general business skills and enjoys product and organization development.
6 Awarded U.S.A Patents in a variety of areas. More applications are about to be filed in the area of data science.
• Machine Learning: Studied and implemented several machine learning and optimization techniques including decision trees, neural networks, Naive Bayes, Hidden Markov models, reinforcement learning, and genetic algorithms, computer vision algorithms, audio analysis algorithms. Experience developing models with "R" using Regression, Logistic Regression, Decision Trees, Boosting, Bagging, and other commonly used techniques.
• Data Mining: Successfully applied use of Jaccard Similarity and similar coefficients as applied to N-Grams, Flajolet-Martin algorithm, Matt Kelsey's Sim-Hashing algorithm for finding similar items. Use of Murmur Hash algorithm. Levenshtein Distance.