Machine Learning

Company: ingenium.agency
Location: New York, New York, United States
Type: Full-time
Posted: 03.SEP.2021
< >

Summary

We have multiple roles ranging from mid level, Senior level and Engineering Manager of Machine Learning up to $225k + bonus + equity NYC or...

Description

We have multiple roles ranging from mid level, Senior level and Engineering Manager of Machine Learning up to $225k + bonus + equity

NYC or Remote

WHAT WE DO
Imagine if every time you went to the doctor you paid cash upfront before you are treated, where every time you rented an apartment you paid 2 years cash upfront, or where your monthly paycheck is frequently delayed for months at a time. Then imagine doing that without a loan, credit card, or even bank accounts. This is everyday life for over 3 billion people in developing countries around the world. We are on a mission to change this by re-inventing the way people access and use credit.
Through a simple API integration to our platform, companies can enable their customers to make purchases and pay bills on credit, or get personal loans. Leveraging proprietary datasets, we build ML algorithms on customer phone records, bank records, and payment transactions to assess credit risk, enabling us to offer credit lines to individuals and small businesses. This credit line can be used to make purchases from a merchant or withdraw cash without the need for point-of-sale hardware or plastic cards. Because of our proprietary data and innovative technical solutions, we are able to provide credit to underbanked customers who are not typically covered by credit bureaus, a critical area of growth for developing countries.

RESPONSIBILITIES OF THE ROLE
As an experienced machine learning engineer, you would own the entire machine learning pipeline from data sourcing and training to model serving, helping us productionize findings from data science into real-world applications. Your primary responsibility will be to develop and maintain production-quality software to host machine learning and statistical models, and make them available to our platform. You will also design and build model training, publishing, and analytics pipelines for a multitude of machine learning models. In addition, you will validate model integrity and monitor performance while providing data scientists with tooling to accelerate their iteration cycles.
Your activities would be:
- Feature engineering for machine learning
- Iterating on and experimenting with models
- Building and maintaining reliable predictive services
- Documenting your work clearly for others to follow
- Implementing analytics pipelines to assess model results
- Setting up data and cloud environments to make data science more efficient
- Quickly learning new tools

In the first 90 days you would:
- Develop pipelines to compute and store predicted lifetime value for any customer that has changed state recently.
- Build models to predict repayment rates on installment loans given a user's previous loan history
- Combine credit scores derived from disparate datasets into a single ensemble score that predicts whether a new customer will be a good long-term customer

WHAT WE ARE LOOKING FOR
Are you a machine learning engineer ready to help us redefine credit for the 21st century? We are on a mission to leverage data from partners around the globe to perform credit scoring for 3 billion people. The opportunities for you to make an impact are limitless.
You should be a clear and concise communicator, with an ability to communicate ideas to a wide range of stakeholders both technical and non-technical. You appreciate hearing different points of view and wait to hear other's point of view before offering your own. You have a pragmatic approach to building systems, see multiple ways of solving problems, and are able to discuss the tradeoffs of each solution. You are technology agnostic with broad depth and breadth of experience using many different technologies.
Ideally you have traveled extensively or have lived in a developing country. You are empathetic, self-aware and respect all cultures. You are fun and enlightening to work with, and you have a good work/life balance with hobbies and interests you are happy to share with others.

HOW WE INTERVIEW AND HIRE
Our interview process begins with an introductory call to help you better understand the opportunity, give us a glimpse into your interests and motivations, and help you decide if this is the right place for you to be your happiest and most successful self. From there, we will conduct a technical screen with one of our engineers so you can show us your skills. If all goes well, you will be invited onsite to interview with an interview panel from our data science and software engineering teams. Our onsite interview includes 3-4 technical rounds, as well as conversations around what it is like to work with us and how you would work with the team on a daily basis. It is designed to assess a broad range of skills so that we can gain a holistic understanding of what you bring to the team and where you shine. We pride ourselves on being transparent throughout the entire interview process with conversations around compensation and the impact you will make.

WHY SHOULD YOU WORK WITH US?
When you come to work with us, you can be assured that your work will be deeply meaningful. You will spend your days solving challenging problems alongside smart and capable colleagues. Daily decisions here have tangible and immediate impact on millions of people. You will be given both the respect and the latitude to drive best-practices for building world-class systems. You will be fully supported by executive management, many of whom have engineering backgrounds and will share your concerns if you say we are accumulating too much technical debt.
One day you will look back and realize that you did some of the best work of your career here. You will have significantly increased your positive impact on the world during your career here. We are growing quickly and operating in a trillion-dollar market with few competitors. Your equity has a high chance of producing significant upside.

OUR TECH STACK
Our technology stack consists of modern tools; we are open to technologies and pick the right tool for the job:
- Python for Machine Learning e.g. (Scikit-learn and PyTorch)
- Python/Scala for data pipelines
- Scala/Java/Python for micro-services and APIs
- Swagger(OpenAPI) for API documentation
- Docker and Kubernetes to package and run services
- AWS for cloud infrastructure
- On-premise servers for data processing and extraction at our partners
Requirements
- Degree in a relevant technical field or equivalent experience
- 8+ years of software or data engineering experience
- 5+ years of work experience building and deploying production machine-learned models
- Ability to own and deliver on large, multi-faceted projects with little guidance
- Experience productionizing code models developed by data science teams
- Experience with frameworks for model serving (e.g., Sagemaker)
- Experience with modern machine learning frameworks like Scikit-learn, Torch or Tensorflow
- Understanding of statistical modeling
- Demonstrable history of building production-quality software infrastructure
- Experience developing microservices
- Experience building data pipelines
- Expert experience in Python
- Some experience in Java

Desirable
- Masters or PhD
- Background in data science
- Experience in classification, regression, clustering, and graph analysis
- Experience with customer behavior modeling

Benefits
- Medical/Dental/Vision - full coverage of health premiums, with 50% covered for spouse and dependents
- 401(k)
- 12-week maternity/paternity leave
- Unlimited PTO
- Monthly contribution for wellness related activities and programs
- A chance to be part of something that makes a significant difference in people's lives

 
Apply Now

Share

Flash-bkgn
Loader2 Processing ...