Data Scientist - AI/ML (Mid & Sr Levels)

What is Spade? Financial institutions process billions of transactions every day across cards, ACH, wires, and third party aggregators. But most of that data is difficult to use. Descriptions are inconsistent, merchant names don’t match, and categories vary by payment type. Spade is a data and AI platform that turns messy transaction strings into structured, verified records — and gives teams the tools to act on it across authorization, attribution, analytics, and AI initiatives. Spade leads the market in terms of merchant coverage, matching accuracy, geolocation data, and speed of transaction enrichment. Customers such as, FIS, Bilt, Mercury, Stripe, alongside many other leaders in fintech and financial services, trust Spade's data to enable personalized rewards programs, accurate applied spending rules, precise analytics requests, and innovative AI-powered features. Spade is a fast growing, Series B company backed by industry experts and top tier investors (including Oak HC/FT, a16z, Flourish Ventures, Y-Combinator, and Gradient Ventures). We’re a lean and execution-oriented hybrid team, passionate about building exceptional products for our growing customer base. We care deeply about diversity of background, experience, and opinion. We value empathy, curiosity, and passion, and strive to create an environment where individuals have autonomy and the ability to take ownership over their work.

At Spade, data is the product — and you'll be one of the people shaping it. As a Data Scientist, you'll build the real-time ML/AI systems that power how top fintechs and financial institutions understand every transaction: from traditional ML and NLP models to AI agents, all running on our proprietary merchant, location, and transaction datasets. Your work won't sit in a research silo — you'll partner closely with engineering and product to take ideas from prototype to production, directly shaping the accuracy, speed, and intelligence customers like FIS, Bilt, Mercury, and Stripe rely on every day. What will you be doing? Own the full lifecycle of ML/AI products. From first prototype to production system serving real customers Build the automated systems behind Spade's data quality. The models and pipelines that keep our accuracy and coverage ahead of the market Set the bar for how ML gets built here. Pushing for models that are not just accurate, but scalable, robust, and production-ready from day one Help shape where the data science team goes next. Partnering directly with leadership on roadmap and priorities (Senior role) Grow the team around you. Mentoring other data scientists and raising the practices we build on (Senior role) Note: We're hiring for both Mid and Senior levels across multiple openings; exact level is determined during the interview process. What experience, skills, and qualifications are necessary? Must Have: 3+ years building and shipping models in Python, in a fast-paced environment (5+ for senior) Worked hands-on with engineering and product, not just in a research silo Strong ML, stats, and data fundamentals (PySpark, pandas, SQL) A product mindset — you navigate ambiguity and optimize for customer value, not just model accuracy A collaborative streak — you take feedback well and care about the team's success, not just your own An AI-forward workflow — coding assistants and LLMs are part of how you already work, and you're excited to push further Are able to work remotely within the US or Canada. We are also open to NYC-based candidates who would prefer to work hybrid (2 days/week) out of our Flatiron HQ. Additional for Senior Level: 5+ years experience, with end-to-end ownership of ML/AI products from idea to production Shipped ML/AI-powered products, ideally customer-facing A track record of mentoring and raising team standards Nice to have: Databricks, data pipelines, Hex Gen AI feature/product development Fintech experience — especially transaction, merchant, or location