Software Engineer, Machine Learning

Snap Finance

About The Position

We are seeking a Software Engineer, Machine Learning to join our Machine Learning team and play a critical role in building and scaling advanced ML systems. This role is ideal for a highly experienced engineer who thrives on solving complex, real-world problems using large-scale, multimodal data. In this role, you will design, develop, and deploy production-grade machine learning models that improve prediction accuracy, reduce risk, and empower consumers in the rapidly growing alternative finance market. You will also help define frameworks, tools, and best practices that elevate engineering quality and productivity across the organization.

Requirements

MS or PhD in a quantitative field such as Statistics, Econometrics, Mathematics, Physics, Computer Science, or related quantitative field.
BS in the fields described below will be considered if skill set and experience are robust
Possess broad and deep technical expertise across multiple areas of machine learning.
Strong software engineering skills, system design experience, and comfort owning services in production.
History of tackling challenging technical problems and involvement in making high-level decisions about technology choices and system architecture.
7+ years experience in one or more of the following areas: machine learning, artificial intelligence, recommendation systems, data mining, or related research
Strong background in Python, Java , or other general-purpose programming languages
Experience with modern sequence based deep learning (e.g., transformers, RNNs, and other attention-based autoregressive models) and multimodal learning (structured + text + graph/time-series).
Extensive experience with traditional classification methods (e.g. Gradient Boosting, Decision Trees, Random Forest)
Proficiency and working knowledge of at least one major deep learning framework (e.g. PyTorch, JAX)
Experience with filesystems, server architectures, and distributed systems
Statistical analysis (e.g., Hypothesis testing, experimental design, hierarchical modeling, Bayesian and Frequentist methods)
Experience with automated workflows: Airflow, Jenkins, etc.
Experience with AWS cloud services such as EC2 and S3
Working knowledge of message queuing, stream processing, and highly scalable data store
Familiarity with common computing environment (e.g. Linux, Shell Scripting)
Strong SQL skills
Proven ability to translate insights into business recommendations

Responsibilities

Develop and innovate on state-of-the-art, scalable ML models leveraging artificial intelligence, machine learning, optimization, and rules-based approaches.
Design and ship end-to-end ML systems, including data pipelines, feature engineering, training and evaluation workflows, online inference, and feedback loops.
Push the boundaries of credit risk modeling, customer behavior analysis, and creditworthiness assessment.
Partner cross-functionally to onboard new data sources, improve data quality, and create durable, high-signal features.
Propose, gather, and integrate diverse datasets to support advanced modeling initiatives.
Assemble and manage large, complex datasets that meet both functional and non-functional business requirements.
Mentor engineers and raise the technical bar through architectural reviews, documentation, and reusable tooling.
Influence technical direction through high-level decisions around system architecture, modeling strategy, and tooling.