Radius Global Solutions - Data Scientist

Essential Job Responsibilities/Qualifications:

- Build and evaluate predictive and decision models to be deployed in production systems, or for research

- Conducting experiments with different types of algorithms and models, analyzing performance, to identify the best algorithms to employ

- Background in applied statistical modeling on large experimental or observational data sets Experience extracting data from a variety of sources, and a desire to expand those skills (working knowledge SQL is required, Spark is a plus) -

- Experience with one or more statistical or machine learning software such as R, Python, etc. Must showcase past work through published articles/GitHub/social media 6+ years of work experience in data scientist projects

- Applying Natural Language Processing and predictive modeling to understand client's search query intent so we can offer relevant content

- Using machine learning to develop self-correcting algorithms to improve recommendation Develop models to help predict retention outcomes and identify levers to improve outcomes

- Leverage internal and external big data to understand client's company level priorities, competitive landscape and deliver targeted support.

Education / Certification / Special Skills:

- Graduation in Engineering, Math- s, or Statistics from reputed University

- 3-4 years of experience in building predictive models, recommendation systems, or NLP/text mining tools. Prior experience in NLP is highly preferable

- Proficiency in Statistics and Machine learning. literature: Linear algebra, Matrix factorization, linear and non-linear feature transformation, Linear/Nonlinear Modeling, Un/Semi/Supervised modeling, High dimensional methods.

- Familiar with the foundational approaches to the major data science disciplines, such as data preparation, advanced statistics, machine learning, simulation, and natural language processing

- Experience and proficiency with various programming languages (e.g., Python), machine learning tools (e.g., scikitlearn), statistical packages (e.g., SciPy)