Stilt (YC W16) is building a bank focused on 45 million immigrants in the US. Immigrants are traditionally shut out of the financial system because they lack a financial identity. We are building technology to democratize access to financial services.
Improving access to financial services for everyone, especially for the underserved and immigrants has never been more important. They contribute $1.6T to the economy, have built many $100B+ companies, and generated millions of jobs. Still, immigrants don't get the services they deserve. We are building technology to help immigrants from day 1 of their arrival. Since launch, we have helped hundreds of thousands of immigrants from 160+ countries. We are growing fast and now at an inflection point in our journey to help millions of immigrants.
We are based in San Francisco (open to remote), founded by an immigrant team with expertise in finance, technology, and machine learning. 70% of the team is immigrants and from underrepresented backgrounds. We are working hard to make financial services simple by using non-traditional data, building a modern scoring and decision engine, and improving operational efficiency.
It is a challenging and fulfilling opportunity for someone looking to make a difference in the lives of immigrants across the world. As we rewrite the approach to banking, we are looking for a Data Scientist who is experienced, knowledgeable, and believes in making this happen with us.
Continuously explore new alternative data sources to add incremental predictiveness in the models though orthogonal signals/features.
Build end to end machine learning models, from design, learning, evaluation, validation & monitoring.
Create, expand, explore, rank & maintain logs of innovative internal feature sets for credit, pricing & fraud.
Expand the performance data using organic & synthetic methods wherever possible.
Develop automation capabilities & advanced dashboards required for faster processing and monitoring.
Own end to end model implementation, model iteration, model versioning, for production and sandbox environment
Collaborate with the engineering and product teams to implement, ship, test and monitor the risk models.
Quantitative Background: Bachelor’s (preferably Master’s) degree in Computer Science, Statistics, Mathematics, Financial Engineering etc.
Programming Ability: Expert knowledge of Python or R, & SQL. Experience using cloud technologies (AWS, GCP) and distributed data/computing tools.
Proficiency in writing and maintaining production level code. You will ship what you write.
ML Delivery Experience: Built key ML system/s from large raw data to production & scaled, monitored & improved it over 1-3 years. Right candidate with more experience (3-6 years) can also be considered for senior position.
Statistical Mindset: Understanding of the right tools for a given data analysis. Focussed on model selection, interpretability, biases, explainability & monitoring.
Data Friendly: Revel in data cleaning, feature engineering & data generation.
Clear Communicator: Able to collaborate across functions and explain difficult concepts in written, visual & verbal.
Self Organized: Belief in data & code review/versioning, reproducible work with clear/concise documentation.
Self Starter: Willing to quickly learn new things, test & share with the team.
The opportunity to collaborate with a team of creative, fun, and driven colleagues on products that have an immediate and significant impact on people's lives
Comprehensive medical, dental, and vision coverage