Data Scientist

Vantor

24d•$135,000 - $170,000•Remote

About The Position

Vantor is currently seeking a Data Scientist to lead the development of statistical and machine learning models to support our FALCON effort. This role can be performed remotely within the continental United States. The ideal candidate will derive these models to detect kinematic behaviors leveraging live and historical data. Using these models, the candidate will develop and run simulations to inform the development team on approaches to incorporate analytics into the system. This is an exciting opportunity to discover and apply data science techniques to solve unique and evolving problems. As a Vantor team member, you will have the opportunity to closely support our mission partners, and your work will have a direct impact on building mission-focused software capabilities that support operational awareness, data-driven analysis, and timely decision-making. In this role, you will work closely with software engineers, data scientists, analysts, and customer stakeholders to build, enhance, and sustain applications and data pipelines that help transform complex data into actionable insight. About Us: We are a multi-disciplinary software development and data-focused team supporting mission partners through rapid prototyping, iterative development, and operationally relevant technical solutions. Our diverse background of experience in mission support, software engineering, and applied data science serves as a catalyst to solve unique and challenging intelligence problems in support of operational users and their on-going activities. Prototyping and frequent, iterative feedback are core to our delivery approach, anchored by a need to ensure accuracy, reliability, and timeliness in support of our customer’s mission. Culture matters! The FALCON team values clear communication, ownership, technical curiosity, and the ability to contribute ideas without ego while fostering each other’s growth through feedback and flexibility.

Requirements

Must be a US citizen.
Current Top Secret security clearance and/or CBP/DHS suitability.
Good working knowledge of Python and libraries such as pandas, numpy, scikit-learn, matplotlib, scipy
Experience in processing/cleaning and analyzing time series and/or geospatial data
Strong statistical background in areas such as statistical testing, regression, and probability
3+ years of professional experience in applying machine learning techniques to time series and/or geospatial data
Strong verbal and written communication skills
3+ years of professional experience with database / data file system such as PostgreSQL, HDFS
3+ years of professional experience with version control systems such as Git
3+ years of professional experience with time series event forecasting
Ability to understand and integrate new machine learning algorithms and technologies
Bachelors in Data Science, Data Analytics, Computer Science, Physics, Mathematics, or other related discipline with 5+ years of industry experience of the data science field
Experience with scoring and measuring algorithm performance
Data Visualization of multi-source, multi-dimensional data, and analytic results in both real-time and for presentations
Experience conducting model feasibility research and algorithm development for machine learning
Ability to multitask, prioritize, and manage time efficiently
Wide breadth experience with machine learning algorithms and approaches
Current knowledge of the latest industry trends; Ability to articulate trends and their potential clearly and confidently
Experience in working on teams following development methodologies such as Agile Scrum or Kanban

Nice To Haves

Master’s degree
Experience with Deep Learning technologies (Pytorch, Keras, Tensorflow)
Experience with radar data
Experience with data corellation

Responsibilities

Lead team in designing analytic solutions that meet customer needs
Enhance existing analytic solutions to ensure quality and performance
Integrate Data from multiple sources to create a common operating picture
Select and implement appropriate statistical analyses and scoring metrics to evaluate performance of existing algorithms
Create training and test datasets from multiple sources to enhance existing algorithms
Perform data processing activities such as data cleansing and validating as well as other Extract Transform Load (ETL) functions
Derive and produce Analytic Reports and Presentations for internal and external stakeholders
Identify and implement data visualization for analysis, presentation, and end-user UI needs
Perform feature engineering, classifier optimization, event forecasting, and anomaly detection
Interface with external stakeholders to decompose data science mission needs
Produce data science processes, results, and approach documentation
Select and implement industry machine learning algorithms to enhance or compete with existing algorithms