Data Scientist/Machine Learning Engineer

at  Intelligent Audit

DATA SCIENTIST/MACHINE LEARNING ENGINEER

As a Data Scientist at Intelligent Audit, you will design, develop and test new Machine Learning tools on large logistic datasets. You will perform exploratory analysis on propriety data, and use those insights to direct your technology development. You will work closely with a team of data scientists, analysts, and developers to assist at every phase of development, from initial interpretation to production-ready roll-out. You will maintain, test, and improve your technology to ensure high efficacy throughout the full software lifecycle.

Qualifications/Requirements

• MS + 3 years experience or PhD in Computer Science, Electrical Engineering, Mathematics, Physics, Statistics, or related fields with a focus on Machine Learning.
• At least 2 years experience with structured multivariate time-series data.
• At least 5 years experience in Python with a focus on data science libraires: Jupyter Notebooks, visualization libraries, Pytorch, XGboost or similar, Numpy, pandas, etc.
• At least 2 years experience with deep learning architectures, especially transformer models.
• At least 3 years experience with work on Linux cloud and/or remote software clusters for high performance computing on big data

• Work with the data science team to develop and implement various algorithms on shipping and billing data.
• Explore, visualize, and analyze internal and external datasets to discover and leverage new insights.
• Employ internal, enterprise, and open source data science software libraries, primarily in the Python ecosystem.
• Focus on new algorithm development from prototype to production.
• Ability to work with our team to deploy monitoring solutions into new ML products.

Qualifications/Requirements

• MS + 3 years experience or PhD in Computer Science, Electrical Engineering, Mathematics, Physics, Statistics, or related fields with a focus on Machine Learning.
• At least 2 years experience with structured multivariate time-series data.
• At least 5 years experience in Python with a focus on data science libraires: Jupyter Notebooks, visualization libraries, Pytorch, XGboost or similar, Numpy, pandas, etc.
• At least 2 years experience with deep learning architectures, especially transformer models.
• At least 3 years experience with work on Linux cloud and/or remote software clusters for high performance computing on big data.

Preferred Characteristics

• Ph.D. focusing on cutting edge Machine Learning techniques.
• Prior experience with logistic data.
• Deep expertise in one or more of: transformer networks on structured data, tabular time-series data, machine learning forecasting methods
• Publications, conference proceedings, and/or sample code portfolio to demonstrate proficiency of machine learning methods is a plus.