Senior Data Scientist, Methodologies

At Tilt, we see a side of people that traditional lenders miss. Our mobile-first products and machine learning-powered credit models look beyond credit scores, using over 250 real-time financial signals to recognize real potential. With millions of customers worldwide, we're not just changing how people access financial products — we're creating a new credit system that backs the working, whatever they're working toward.

At Tilt, we're constantly exploring new ways to understand financial behavior and reduce risk. The work you do in this role will go directly into the foundational models we're building for our products.

We're looking for a Senior Data Scientist to join our Methodologies group — a role focused on building and advancing foundational modeling approaches. You'll build and test deep learning methods such as transformers to improve how we understand financial data and make lending decisions.

This is a great role for someone who's deeply curious about new modeling techniques and wants to see their ideas make a real difference. You'll work with a small, experienced team of data scientists and engineers, taking projects from first idea to working model on financial data challenges — from credit decisioning to customer behavior!

You'll also be at the forefront of how data science is practiced in the age of AI agents. Our team builds with agentic tools every day, and you'll use them in your own work and help build the specialized agents that speed up both DS and business workflows.

We're looking for someone who enjoys learning, experimenting, and collaborating — a person who can connect technical exploration to meaningful business impact. If you're excited by applying new methodologies in ways that help people access fairer credit, you'll fit right in.

• Build, train and evaluate deep learning models on Tilt's financial data.

• Ship models and model components that plug into Tilt's existing ML pipelines to improve credit modeling and loss prediction.

• Own your projects end to end, from hypothesis to a model in use, with general direction from the team's leads.

• Work closely with data scientists, engineers, and product partners to turn your results into practical solutions.

• Run representation learning experiments — including pretraining and fine-tuning — on real financial data, with a clear design up front and an honest read on what worked.

• Share findings and help peers pick up new deep learning methods.

• Measure the impact of your models not just by accuracy, but by how they improve outcomes for Tilt's customers and partners.

• Use agentic development tools (e.g., Claude Code, Codex) to speed up experimentation, feature engineering and model iteration.

• Build and improve specialized agents that support DS workflows.
  

• Hands-on experience building and training deep learning models

• Comfort working with modern ML frameworks (PyTorch, TensorFlow, or similar).

• Experience applying ML to real-world problems, ideally in financial services (credit, lending, payments, or banking).

• Experience taking a project from an open question to a measurable business outcome.

• Clear, thoughtful communication — you can explain technical ideas in ways others can engage with.

• Bonus: hands-on experience building with LLMs or agent frameworks, or excitement to learn. You see agents as a way to multiply what a small, senior team can do.