Job Description - Data Scientist / ML Engineer (Credit & Lending)
Our fintech bank client is building the most audacious banking experience you can imagine - everything you wanted from your bank but never got. Now's your chance to make it happen and upgrade an archaic industry forever!
A well-funded, fast-moving start-up in Bangalore. Our funding and seed partners are well-known and reputed international start-up fund houses in the FinTech space.
Job Description
We have millions of active monthly visitors, we have access to huge amount of data and insights, which will enable us to take our product to the next level. Our cross functional teams are made up of Data Scientist, Software Engineers and Data Engineers. We are solving real life, current problems and utilising Machine Learning / Deep Learning techniques alongside Software Development to provide our users with a unique Experience.
We are looking for an outstanding, hands -on Data Scientist / Machine Learning Engineer, adept at not only understanding and interpreting data, but also building models and influencing change in the organisation. You should have a proven record of working with large amounts of data, leading the development of technical solutions and building production -ready machine learning models.
You should be a self -starter with an entrepreneurial spirit, able to think outside the box and take initiative. You should be smart, passionate and dedicated to building a great business.
• Leverage advanced Machine Learning and Big Data Analytics to credit risk score and assess millions of users using more than 1,000 data points over a long period of time wrt various dimensions.
• Build ML based credit underwriting models that can serve the under-banked or thin file borrowers by using alternate data from social platform and mobile phone. Experience in the usage of nonstandard data in decision making workflow will be an added advantage.
• Create End-to-end credit assessment Data Science solution that can suggest best possible loan offer to customers.
• Big Data platform to analyse customer data from Web, Social and Mobile APP .
• Develop suitable data mining models on product domain like PL, consumer products, Ability to Identify variables that could have raised risk beforehand and use the variable to create a prediction model for risks. Candidate should have created at least 1-2 risk models and tested the efficacy of the modelling output.
Location - Bangalore
2 - 6 years
B.Tech/B.E , -B.A in Statistics ,or M.Tech , MSC in Statistics , M.A in Statistics ,and Ph.D/Doctorate in Statistics
Responsibilities
• Work on difficult challenges in Deep Learning, Natural Language Processing, User Experience, High Load and Scalability, Growth Hacking, Credit and Risk Analysis, Loan Distribution and Collections, etc.
• Become the truly world class at what you do.
• Freedom to build and own major pieces of the India's largest credit engine.
• Make a huge contribution in solving the problem of financial inclusion in India.
• Find connections across different data sources and build models leveraging those findings.
• Take ownership of the full cycle of a credit model from ideation through training and testing to production.
• Closely collaborate with the engineering team to integrate Machine Learning models with the backend code.
• Constantly monitor model's performance and quickly adapt to the constantly changing environment.
• Share your knowledge of data science with the engineering team
Data Science , Machine Learning , Python , PyTorch , Tensorflow , scikitlearn , Pandas , Matplotlib , Keras , Kaggle
Qualifications
• Minimum of 2 years of work experience in Data Science.
• Experience in Data Science in application to lending & finance.
• Bachelor or master’s degree in engineering, Computer Science, Operational Research, Statistics, Mathematics, Physics or a related field.
• Mastery of Python, SQL, and Python ML libraries.
• Solid knowledge of applied statistics and machine learning.
• Experience of building / deploying models and maintaining them in production.
• Experience in data science models for credit / risk / fraud.
• Experience with PyTorch, Tensorflow, scikit-learn, pandas, matplotlib, Keras, etc.
• Experience with natural language processing and social network analysis.
• Competitive experience on Kaggle, ACM ICPC, IMO/IOI (Big Plus).
• Enjoys finding novel solutions to hard technical problems.
• Ability to clearly communicate and listen intently.
• Wise, curious and independent learning machine.
• Record of academic publishing in related conferences and/or journals is a plus.
• Having a Kaggle or Github Profile to share would be awesome!