Applied Deep Learning, Graduate Intern (Master's or PhD)

Company Description

It all began with an idea at Block in 2013. Initially created to alleviate the inconvenience of peer-to-peer payments, Cash App has evolved from a basic product with a single function to a dynamic ecosystem, creating distinctive financial products, including Afterpay/Clearpay. This provides a superior method for our 47 million monthly active customers to send, spend, invest, borrow, and save. We aim to redefine the world’s relationship with money to make it more understandable, immediately accessible, and universally obtainable.

Currently, Cash App has thousands of employees working worldwide across office and remote sites, with a culture focused on innovation, collaboration, and impact. We have been a distributed team from the beginning, and many of our roles can be performed remotely from the countries where Cash App operates. Regardless of the location, we adapt our experience to ensure our employees are creative, productive, and content.

Explore our locations, benefits, and more at

Job Description

This opportunity is exclusively available to students presently enrolled in either a Masters or PhD program and offers an 8-month term (with a chance for extension) on Cash App's Risk AI team beginning in Summer or Fall of 2024. If you've already graduated (or are due to graduate before May 2023) please apply to one of our full-time roles.

Machine Learning is a crucial part of how we design products, operate, and carry out Cash App's mission to serve the unbanked and disrupt traditional financial institutions. Our massive scale and deep pool of transaction data offer limitless opportunities to leverage artificial intelligence to better comprehend our customers and introduce new products and experiences that can elevate their lives. We are a highly creative group that prefers solving problems from first principles; we progress quickly, make incremental changes, and deploy to production daily.

The goal of this project is to systematically examine and validate advanced sequential models (including bi-directional RNN, auto-regressive CNN, transformers, and neural controlled differential equations) on time-series data produced within Cash. Cash App collects a range of signals about how our customers interact with the platform - we will ascertain the optimal way to utilize these data employing cutting-edge deep learning methods.

Deep sequential models offer the potential to significantly enhance our ability to detect fraudulent behavior while reducing the extensive (and hence costly) process of manual feature creation and curation. Models will be benchmarked for automated extraction and detection of fraud patterns within sequential transaction data (e.g., cash in, cash out, p2p, etc).

Duties during your term will include:

• Formulating standardized and reusable datasets for consistent benchmarking and testing of sequence models
• Providing a quantitative evaluation of the advantages and drawbacks of different model classes based on accuracy, precision/recall, training cost, training time, data requirements, and interpretability
• Building a modular and well-documented codebase which can be easily employed for other sources of sequential data within the Block ecosystem

Technologies we use (and teach):

• Python, NumPy, Pandas, , TensorFlow, keras, JAX, Julia
• MySQL, Snowflake, GCP/AWS, and Tableau
• Java

Qualifications

You have:

• 1-2 years of practical experience with applied Deep Learning
• Demonstrated ability to implement neural network architectures described in literature using frameworks such as PyTorch or Tensorflow
• Experience with advanced techniques like graph embeddings, irregular sequence modeling and time-series forecasting, uncertainty quantification, anomaly detection, and neural ODEs is highly desirable
• A comprehension of the link between the software and models you craft and the experience it delivers to customers
• A curious, passionate, growth-oriented mentality

Additional Information

Block adopts a market-based approach to compensation, and pay may differ based on your location. U.S. locations are grouped into one of four zones based on a cost of labor index for that geographic area. The starting salary of the successful candidate will be determined based on the candidate's work location and may be adjusted in the future.

Zone A: USD $51.00
Zone B: USD $48.45
Zone C: USD $45.90
Zone D: USD $43.35

To determine a location’s zone assignment, please refer to this . If a location of interest is not listed, please consult a recruiter for further information.