Data Scientist Semi Senior

About Us:

Fligoo is developing the next generation of AI technology for large customer-based enterprises. Fligoo’s technology leverages AI to allow the most important financial services & wealth management firms in the world to understand their customers, increase sales, predict client attrition, retain advisors, and increase ROI, among others, significantly growing and protecting assets. Companies we partner with include Wells Fargo, Broadridge, Bradesco, Mastercard, Basf, among others.

2-min video: https://vimeo.com/906708649

Job Purpose

The Data Scientist is responsible for analyzing data sources in a business context to propose and implement an analytic approach to solve a business problem. The ideal player is a competent data wrangler with broad experience in several domains, who enjoys analyzing and solving problems. He or she will translate data findings into business insights, so the data scientist must be comfortable interacting with data and getting correct conclusions from them and implementing a proper analytic task to solve the problem. The Data Scientist will provide support on tasks related to data preparation, help to define and implement the analytic tasks, and guide during the development and deployment of a Data Science solution.

Location: Córdoba Capital (not fully remote). 

Position: Full-Time 

Responsibilities

• Maintain communication with the stakeholder to understand the business and the pain points raised by the client.
• Define required data to address the pain point and design a solution that adds value to the business. Process the data in the most effective way.
• Developing an EDA that helps us to validate data with our client and raise insights and results through data story-telling resources.
• Identifying which kind of problem we face (classification, regression, time series, etc.), and selecting the best solution approach to add value in the shortest time.
• Implement data processing and feature engineering to make data available before starting training and testing the model.
• Assess the effectiveness of data by conducting data quality checks.
• Design, build, tune and test algorithms and deploy the models. It is crucial to use best practices that allow you to reproduce the same result in the test and production environment.
• Developing a strategy to validate the model’s results in production.

Qualifications

1. Academic training.

• Degree in Computer Science, System Engineering, Statistics, Mathematics or other quantitative fields.

A master's or Ph.D. in those fields is a plus.

2. Technical Skills.

• Experience with data science toolkits, such as Python, Jupyter notebooks, Spark or R. Knowledge of OOP paradigm. 
• Experience with Python data science libraries such as Pandas, Numpy, Scikit-learn, keras, XGBoost and LigthGBM.
• Experience with data visualizations tools such as Matplotlib, Plotly, Seaborn or GGPlot.
• Experience with AWS cloud infrastructure (i.e. S3, SageMaker, Athena, Lambdas, etc.)
• Proficiency in using task management tools like Trello or Jira and knowledge of the Scrum framework.
• Experience of code versioning through a system like Git, or Bitbucket.
• Virtualization (Docker).

3. Other Skills

• Advanced English.

Experience

• 2+ years working with real-life projects.
• 2+ years working with Python creating data pipelines to process data or to train machine learning models.
• 2+ years performing project tasks and bugs tracking on some platform (e.g. JIRA, Trello).
• 2+ years performing this kind of analytics over real data sources:

- Descriptive Analytics.

- Diagnostic Analytics.

- Prescriptive Analytics.

• 2+ years performing basic charts on real data sources:

- Descriptors of distributions of values (e.g. boxplot, histogram, pie-plot).

- Correlation to a target variable (e.g. scatter, correlation matrix).

- Time series plots.

- Variable importance.

- Correct reporting in terms of business language.

• Feature Extraction on real-life projects over these data kinds: Tabular data; Time series & Text.
• Experience with tree-based algorithms (e.g. Random Forest, Gradient Boosting Machines).
• At least one real-life project developed for these Machine Learning tasks:

- Supervised Learning.

- Unsupervised Learning.

• 1+ years performing communication tasks regarding results of analytics.
• At least 1 real-life project having an A/B testing campaign performed.

#BuenaOndaSiempre #RevolutionizingWealthManagement