Senior machine learning engineer

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.

The Role

Every buyer, seller, and lender on Alt is acting on a number our models produced. Alt Value prices the card. The underwriting model sizes the advance. Those two systems are the difference between a marketplace and a handshake, and they are the closest thing we have to a moat.

We've proven model-driven pricing works. This role takes it from working to excellent: more coverage, better accuracy, lower cost to run, faster to refresh. You'll own the full lifecycle — feature generation, training, validation, deployment, serving, and the monitoring that catches drift before a customer does.

This is not a research seat. The models exist. What they need is someone who treats production as the deliverable.

The metric you own: Model-Based Pricing Coverage — the percentage of cards confidently priced by models rather than by hand. Supporting KPIs: pricing accuracy (% error), pricing freshness (end-to-end orchestration time), and underwriting performance (advance disbursement rate against target default rate).

Most people who are great at this have owned a model in production where being wrong cost money — pricing, risk, credit, or fraud — not a notebook that got handed to someone else to deploy.

What You'll Own:

• Leaner, sharper pricing. Cut infrastructure cost meaningfully while improving accuracy, especially on high-value assets where being wrong is expensive.
• Underwriting from good to great. Iterate the model to maximize cash advance disbursements without breaching risk thresholds or default targets.
• The full ML lifecycle. Feature generation and training through deployment and monitoring. No handoff, no throwing it over a wall.
• The production path. The models' AWS infrastructure and the pricing APIs themselves — capacity planning, autoscaling, latency, and diagnosing the memory and timeout failures that only show up at scale.
• Experiments that settle arguments. Design and run backtests to find and validate features that actually move predictive power and coverage.
• Domain depth. Work directly with our Expert Pricers until your model changes reflect real market judgment, not just what the data allows.

What Great Looks Like (6 Months):

• Shipped leaner, more accurate pricing models. Infrastructure cost is meaningfully down and accuracy is up, especially on high-value assets.
• Moved underwriting from good to great. More disbursement, no breach of risk thresholds.
• Earned trust with Expert Pricers. You're their go-to partner, and they can tell your changes reflect the market.
• Hardened the production path. The pricing APIs are faster, more observable, and easier to reason about, with drift monitoring in place before it reaches customers.

How You'll Use AI Here:

We don't want to hear that you use Claude every day. Everyone does. We want to know what you've built with it. Concretely, in this role:

• Build an agent that reads a batch of new comps and flags the ones our model is likely to price badly, before a pricer has to catch it by hand.
• Use foundation models for feature extraction from unstructured card and listing data — condition language, provenance notes, auction descriptions — and get real lift out of it.
• Stand up a backtest harness you can talk to, so evaluating a feature idea is a conversation rather than a two-day branch.
• Put an MCP server over the model registry and prediction logs so "why did this card price move" is a question, not a query.
• Use Claude Code or Cursor as the default way you work through a refactor or an infra migration, not as autocomplete.
• If you've built agents, worked with the API directly, written skills or MCP servers, or shipped internal tooling your team depends on — lead with that.

What You Bring:

• 7+ years engineering, with 5+ years building and shipping production ML/AI models.
• Production-grade Python and SQL, including custom feature-engineering pipelines — not just off-the-shelf scikit-learn. Time-decay weighting, leakage-safe k-fold cross-validation, cascading fallback and imputation logic.
• Gradient-boosted or ensemble estimators trained and validated against strict accuracy tolerances, with segment-specific tuning by category or asset type.
• LLMs and foundation models in production, for both internal tooling and user-facing product.
• MLflow or a comparable tool for experiment tracking and model registry/versioning.
• Production model-serving on AWS that was yours — capacity planning, autoscaling, and diagnosing memory and timeout failures at scale.
• CI/CD, production workflow orchestration, and IaC.
• A pragmatic bias. Value delivered incrementally over the perfect rebuild.
• Bonus: real-time or low-latency serving at scale. Startup experience. You collect, or you have opinions about the collectibles market.

How We'll Interview You:

We'll be specific so you can prepare. Before any of it: download the app, buy, bid, and sell. Explore our industry. Every round assumes you've used the product, and we expect your point of view to sharpen as you go.

1. Recruiter screen — 25 minutes. Come ready to talk about the metric you own today, why Alt specifically, and how you're actually using AI. We'll answer your questions and align on comp.
2. Hiring manager with Dae, Head of Data — 45 minutes. Be ready to go deep on a model you took to production and kept there: the systems design, what you owned, where it broke, and what you'd do differently.
3. System design— 45 minutes. Design a model-serving path under real constraints. We'll push back on at least one of your choices on purpose — how you take that matters as much as the design.
4. Team interview- 45 minutes. How you work with the people who depend on your models, including our Expert Pricers.
5. Dae — 30 minutes, then Leore, our founder and CEO — 30 minutes. Everyone who joins Alt meets Leore. Come with a point of view on where you'd take our pricing intelligence.

What we offer:

• We cover 85% of your medical, dental, and vision, and up to 50% for dependents. HSA/FSA available.
• Flexible PTO that people actually take.
• Parental leave at full salary.
• $200/month wellness + $100/month home office stipend.
• Free DoorDash membership, because dinner shouldn't be a decision.
• Remote-first (for most positions), with WeWork access when you want a room with other humans.
• 401(k).
• Alt Equity to all full-time employees.