Data Scientist

About Appgate

Appgate is an industry leader for secure access of remote applications, servers, networks, cloud resources and more. Appgate SDP (Software Defined Perimeter) is our flagship Zero Trust Network Access offering that replaces antiquated hardware-defined and network perimeter-centric (i.e., VPN) approaches to infrastructure security. Our market-defining architecture of a direct-routed data plane has clear advantages. SDP has proven track record of ROI savings for our customers.

We work creatively in a supportive yet challenging environment. Our teams are technical owners of the components they produce, creating an inspiring, innovative, and collaborative culture. Within Appgate, you will be surrounded by the world’s best ethical hackers, security experts, machine learning experts and software engineers.

About The Position

Actively participates in defining, developing, evaluating, and implementing prototypes of artificial intelligence models to address cybersecurity challenges, collaborating with the product and research and development teams.

Responsibilities And Duties

• Leads business problem-solving projects using Machine Learning techniques under the supervision of the data scientists lead.
• Participates in defining the requirements for the ML prototype to be developed, collaborating with the product and development teams. Also, responsible for defining the necessary specifications for the training, validation, and testing datasets.
• Collaborates in implementing data collection and data cleansing using ETL (extraction, transformation, and loading) processes with the data engineer.
• Designs and develops prototypes of machine learning models compatible with the company's products, under the supervision of the data scientists lead, with the product and development teams participation.
• Evaluates the proposed solutions using performance metrics aligned with the chosen approach, such as metrics derived from the confusion matrix (accuracy, precision, recall, FAR, FRR, Matthews coefficient, and F1) for clustering approaches, or proximity metrics (MSE and R2) for regression models.
• Collaborates in the validation and implementation processes of the ML model in the production environment. Additionally, contributes to the creation of model performance monitoring processes aimed at automating continuous improvement.

Qualifications

• 2 years and a master's degree in areas such as software development and artificial intelligence.
• Solid knowledge and use of Python in:
• Data structure, software architecture and unit testing.
• Signal and image processing.
• Data analytics frameworks such as: Pandas, Spark, Matplotlib, among others.
• Modeling frameworks such as: Scikit Learn, Tensorflow, Pytorch, or similar.
• As well as skills in Linux and cloud environments such as AWS.
• Knowledge of model management frameworks such as MLflow is desirable.