Brief Description of position:

mPokket is a rapidly growing and well-funded fintech startup in the lending domain. We offer micro loans to college students and young professionals via our mobile app. With more than 11 million loans disbursed, we are among the largest and most rapidly growing digital lenders in the country. mPokket has been profitable since 2018 and is adequately funded. In our last Series A round in Feb 2020 we were backed by a US based private equity firm. As we look to scale the business another 10x-20x over the next few years, we are looking for ambitious and talented individuals who want to be part of this amazing journey.

We are looking for a Lead Data Scientist to lead a team of data scientist and help us gain useful insight out of raw data.

Lead Data Scientist responsibilities include managing the data science team, planning projects and building analytics models. You should have a strong problem-solving ability and a knack for statistical analysis. If you’re also able to align our data products with our business goals, we’d like to meet you. Your ultimate goal will be to help improve our products and business decisions by making the most out of our data.

Key Responsibilities

• Responsible for overseeing the data scientists team and data specialists
• Teach, lead, and counsel colleagues on new techniques or solutions
•  Collaborate with data and software engineers to enable deployment of sciences and technologies that will scale across the company’s ecosystem
• Responsible for the conception, planning, and prioritizing of data projects
• Responsible for building analytic systems and predictive models as well as experimenting with new models and techniques
• Ensure that data projects align with organizational goals

Minimum Qualification

• Master's degree in Computer Science, Operations Research, Econometrics, Statistics or related technical field
• 10 to 12 years of experience solving analytical problems using quantitative approaches
• Experience communicating quantitative analysis results
• Knowledge with relational databases and SQL
• Development experience in any scripting language (PHP, Python, Perl, etc.)
• Knowledge of statistics (e.g., hypothesis testing, regressions)
•  Experience manipulating data sets through statistical software (ex. R, SAS) or other methods

Technical Skills -

Must have –

• Programming – Python (Preferred) / R
• ML Models – i. Regression – Linear, Logistic, Multinomial, Mixed effect
• Classification – Bagging & Boosting (Random Forest), Decision tree, SVM
• Clustering – K-Means, hierarchical, DB-Scan
• Time series – ARIMA, SARIMA, ARIMAX, Holt-Winters, Multi TS (VAR), UCM
• Neural Networks (Deep learning), Naive Bayes
• Excel and SQL
• Dimensionality Reduction – PCA, SVD etc.
• Optimization Techniques – Linear programming, Gradient Descent, Genetic Algorithm
• Cloud – Understanding of Azure / AWS offerings, Setting up ML pipeline of cloud

Good to have –

•  Visualization – Tableau / Power BI / Looker / QlikView
• Data management – HDFS, Spark, Advanced Excel
• Agile Tools – Azure DevOps, JIRA
• Pyspark
• Big Data/Hive Database
• IDE: Pycharm

Location

Bangalore

Minimum Qualification:

PostGraduate