$$
{{ $t($store.state.user.experience_value_in_dollars) }}
Junior
{{ $t($store.state.user.experience_search_name) }}
0
jobs
Flexible data scientist with strong engineering skills for productionisation
Shaun Gupta
,
London, United Kingdom
Experience
Other titles
Skills
I'm offering
An Oxford PhD in Particle Physics and S2DS fellow with a large amount of experience acquiring, cleaning and analysing large datasets (>1TB) using Python, C++ and bash, with experience in R, Java and C through additional university and Coursera courses. Experience using statistical methods such as least chi-squared fitting and Gaussian kernels, as well as machine learning algorithms such as neural networks and classifiers. Strong programming, mathematical and data analysis skills are complemented by exceptional communication skills,
Have experience working on POC/validation projects, all the way to integrating ML solutions in production systems.
Have experience working on POC/validation projects, all the way to integrating ML solutions in production systems.
Markets
United Kingdom
Language
English
Fluently
French
Good
Ready for
Larger project
Ongoing relation / part-time
Full time contractor
Available
My experience
2019 - ?
job
Senior Data Scientist
IQVIA.
Continuation of Data Scientist role, with further emphasis on productionisation of Scientist existing python packages via CI and coordinating and implementing pipelines for
model deployment enabling automated refreshes of patient/provider lists for clients. Additional technologies used include Docker, Airflow, Jenkins.
model deployment enabling automated refreshes of patient/provider lists for clients. Additional technologies used include Docker, Airflow, Jenkins.
Python, Docker, Jenkins, Deployment, Health, IMS
2017 - 2019
job
Data Scientist
IQVIA.
Worked as part of a SCRUM team. Delivered client projects, using a variety of data sources (clinical trials, US medical claims), with different classification goals (identifying patients with rare diseases, understanding brand/drug initiation patterns, identifying patients likely to respond to induction of labour medication). Engineering work includes Python packages for ETL, bivariate statistics, and model application to support delivery of client projects. Recently started experimenting with Neural Networks (LSTM/TCN) via keras using longitudinal patient records to predict rare diseases. Technologies used include Spark (PySpark)/Hadoop, Pandas, sklearn, R (mlR), gensim. Data Science techniques included feature engineering, cross validation, bagging, classification (Logistic Regression, Decision Trees/Random Forests/Gradient Boosted Trees), class imbalance, model interpretation (SHAP, anchors), word2vec
Python, Scrum, Data Science, R, ETL, Statistics, Engineering, Hadoop, Spark, Support, Keras, Feature, Patterns, Science
2016 - 2017
job
Senior Data Scientist
RowAnalytics.
Mentored a team of four PhD/Academics from diverse backgrounds as part of S2DS Scientist London 2017 - produced a semantically normalised Biological Knowledge Graph used to perform biological interpretation of statistical genomic analysis. Developed a predictive model to determine attention given to Metro newspaper adverts. Implemented a duplicate document removal algorithm using micro-clustering and cosine calculations of high-dimensionality sparse vectors. Additional technologies used include C, c types for Python, openCV, ImageMagick, Prometheus, Monit, Google Cloud Platform.
AWS, Mysql, Javascript, Html5, Css, Python, R, Machine learning, Data mining, Data Analysis
2015 - 2016
job
Data Scientist
RowAnalytics.
Worked on projects including implementation of large scale graph databases, creation of an auto-scaling infrastructure for real-time data acquisition using AWS, image analysis to identify adverts on newspapers, and development of web APIs. Made use of structured and un-structured data from sources such as PubMed and DrugBank. Technologies used include graph (Neo4j, OrientDB), SQL (mySQL/SQLAlchemy) and noSQL (mongoDB) databases, AngularJS, Bootstrap, Apache Kafka, Python, HTML5, Javascript, apache2/nginx, Natural Language Processing (NLP), AWS.
Python, Cloud, C, Google cloud, Google Cloud Platform, OpenCV, Google, Calculations
2015 - 2015
job
Fellow
Science to Data Science.
Intense 5 week data science fellowship. Worked on project with RowAnalytics to implement framework to predict drug-drug interactions. Aggregated/analysed big medical datasets using Python (inc. Pandas), NoSQL, Natural Language Processing, neural networks (Doc2Vec), classifiers (Na¨ıve Bayes/Support Vector Machines) and clustering algorithms. Attended lectures on topics such as SQL, Java, Python, Pandas, Spark, Hadoop, R, Machine Learning and Statistics, as well as a wealth of business topics including Finance, Strategy and Marketing.
Finance, Processing, Framework, Science, Natural, Support, Algorithms, Spark, Hadoop, Marketing, Statistics, NoSQL, R, Data Science, Machine learning, Sql, Python, Java
My education
2011
-
2015
University of Oxford
DPhil, Particle Physics
DPhil, Particle Physics
2007
-
2011
University College London
MSci, Physics
MSci, Physics
Shaun's reviews
Shaun has not received any reviews on Worksome.
Contact Shaun Gupta
Worksome removes the expensive intermediaries and gives you direct contact with relevant talent.
Create a login and get the opportunity to write to Shaun directly in Worksome.
38100+ qualified freelancers
are ready to help you
Tell us what you need help with
and get specific bids from skilled talent in Denmark