Benjamin Bergenstein Email and Phone Number

I am currently a lead data scientist with 10 years’ experience in advanced data modeling from inception to production, with a primary focus on NLP (Natural Language Processing), data analytics, and predictive modeling through ML (Machine Learning) and DL (Deep Learning) with LLMs (Large Language Models). I have built many end-to-end data pipelines from ingest to production, as well as trained many NLP models while integrating model performance indicators.I have experience with predictive modeling, classification, and deriving insight from both sparse data-sets, to big data, while facing challenges of computational limitations requiring batch training methods and masking PII. I am accustomed to communicating data insights to various product owners and stakeholders. In addition to hands-on work, I have leadership experience and have managed teams of data engineers and data scientists on several projects.I have worked as a data scientist in the healthcare industry, DoD (Department of Defense), and DHS (Department of Homeland Security) with Secret and Public Trust clearance. BDSO (Biometrics Devsecops), PCIS (Person Centric Identity Services).Modeling tasks I have used regularly (non-exhaustive):Predictive ModelingNLP GraphingGeo DistanceImage RecognitionStatistical ProbabilityIdentity ResolutionMulti-Class ClassificationNER (Name Entity Recognition)Anomaly DetectionBipartite Graph extraction with Deep learningKnowledge Graph extraction with Deep learningSentiment AnalysisGenerative modelingTopic ExtractionNoun Phrase ExtractionRecommender SystemsMonte Carlo SimulationPOS (Parts of Speech) tagging & extractionText SummarizationData AugmentationSentence ClusteringDocument SimilarityText TranslationSpeech RecognitionSpeaker DiarizationText MiningRecommender SystemsPredictive Modeling based on Social MediaWeb Scraping for data ingestionSpeech to TextText to SpeechModels and Libraries Include:SVM, RNN’s, LSTM, Transformers, BERT, RoBerta, DistilBert, XLnet, LDA, DTM, FastText, Glove, Spacy, Pandas, Numpy, Glob, Scikit Learn, Keras, TensorFlow, Linear Regression, NLTK, Gensim, Flair, Flask, PCA, K-means, Bayesian, Markov, AWS Boto3, Sphinx, Levenshtein Distance, GANsLanguages:Python - 8+ yrs.SQL - 8+ yrs.R - 2 yrs.Scala 1Software:Databricks, Spark, AWS, Git, Tableau, Power BI, Windows, Mac, Linux, Microsoft Suite, pgAdmin, Microsoft SQL Studio, SAS Studio, SAS Data Mining, Microsoft Azure, Anaconda, Spyder, MLflow, Streamlit