Quantitative Researcher, Pricing

Alt is unlocking the value of alternative assets, starting with the $5 B trading-card market. We let collectors buy, sell, vault, and finance their cards in one place and we are backed by leaders at Stripe, Coinbase, Seven Seven Six, and pro athletes like Tom Brady and Giannis Antetokounmpo. Our next frontier is real-time pricing at scale—the Alt Value that powers every trade, loan, and product on the platform.

Automatically Priced

Alt Value, our pricing engine, shapes what collectors see in the app and what they can borrow against their cards. This role makes Alt Value more accurate.

This is a hands-on seat. You'll find new signals, build them into our pricing, and decide how our models are used.

What this role is not: a reporting role or a management track.

What it is: testing whether new data predicts price moves, investigating unusual sales, explaining price gaps between marketplaces, and deciding which model to trust when two disagree.

You’ll report to the Head of Pricing Automation and work closely with Expert Pricers, data scientists, and machine learning engineers.

The people who do well here are obsessed with making every decision with numbers, even the uncertainty is quantified.

• New data signals. Identify new signals, from market sentiment to sports outcomes, and validate its predictive power through rigorous backtesting.

• Market manipulation detection. Identify potential market manipulation and unusual activity, and keep it from distorting our valuations.

• Cross-market pricing. Design models for an inefficient market, where the same card can be mispriced from one marketplace to the next.

• Model selection and blending. Evaluate our pricing models and decide which to use, or how to blend them, weighing the trade-offs.

• Release and routing decisions. Decide when a new model version goes live and when to switch routing.

• The bets and the trade-offs. Set your own research priorities, work with Expert Pricers, data scientists, and machine learning engineers, and communicate the reasoning behind price movements.

• Pricing accuracy has measurably improved.

• New data sources have been tested, and the useful ones are in production.

• Potential manipulation is weighted in our valuations.

• Model selection and blending are backed by evidence.

• At least one new tool or method has been adopted into our pricing.

• Expert Pricers rely on your work.

We’re AI-native by default. You’ll stay on top of new models, tools, and techniques, and bring in what improves our pricing.

• A track record of building pricing or forecasting models in production, and familiarity with tree-based models and newer approaches such as large language models, time-series foundation models, and graph neural networks.

• Depth in non-traditional or illiquid assets
  , such as collectibles, art, real estate, or alternative credit. We’re reading the work, not the years.

• Experience combining multiple models or signals
  , through portfolio construction, forecast combination, or ensemble methods.

• Market prediction with alternative data
  , including unstructured sources such as text and sentiment.

• Statistical rigor
  : experimental design, backtesting, and noisy or sparse data.

• Expert SQL and Python.

• Hands-on work building with AI
  , such as agents or internal tools that others rely on.

• Clear communication
  , with a record of explaining complex work to non-technical audiences.

Backgrounds that fit: quantitative research or portfolio construction at an investment firm; statistical or cross-market arbitrage; sports betting or prediction market pricing; credit or insurance underwriting; marketplace pricing or trust and safety.

Before your first conversation,…