Role overview
ML/AI Engineer
Job Title: Machine Learning / Artificial Intelligence Engineer
Location: Hybrid or Remote
Employment Type: Full-Time or Contract
Finalytics is on a mission to make digital experiences in finance relevant, easy, and valuable. The financial organizations that run Finalytics are some of the most advanced at personalization in the country. We are looking for a new team member to help drive the next generation of our advanced personalization platform.
We are seeking a high-impact ML/AI Engineer to join our team and spearhead the next generation of our advanced personalization platform. This role is ideal for a hands-on technologist who thrives on bridging the gap between raw data and production-ready intelligence. We are looking for a AI/ML data scientist that can create recommender models which predict what products people want and how they conduct research (e.g. rates, personal consultation, comparative shopping).
What You’ll Do In This Role
Architect Complex Data Pipelines: Integrate disparate datasets including advertising metrics, web analytics (GA4/Adobe), digital banking transactions, and third-party sources (Census, Credit Bureau).
Build & Deploy Advanced Models: Design, train, and deploy recommender models that predict product affinity, buying intent, and user segmentation as well as learner models that understand how people and business research financial products.
Optimize & Experiment: Test models against historic data and experiment with combinations of algorithms to continually optimize for best results.
Cross-Functional Collaboration: Partner with engineering and product teams to integrate models into our SaaS platform, ensuring seamless real-time personalization.
Hypothesis-Driven Development: Analyze model performance in the wild and develop data-driven hypotheses for iterative algorithmic improvement.
What we're looking for
Proven ML Expertise: Demonstrable experience building recommender systems using frameworks such as Collaborative Filtering, Matrix Factorization, and Reinforcement Learning.
Model Experience: Experience creating multiple models such as XGBoost, K-Means Clustering, and predictive modeling.
Platform Development: Strong experience integrating predictive models into live SaaS environments.
Programming: Proficiency in languages such Python, SQL, Java, or R
Tools: Advanced experience in TensorFlow, PyTorch, JAX, Jupyter Notebooks, or R-Studio.
Domain Knowledge: Experience in FinTech, banking, or credit unions.
Advanced Data Sources: Familiarity with credit bureau data, segmenting tools (e.g., Claritas), or advertising APIs.
Emerging AI: Experience building agents or integrations with LLMs (e.g., via MCP or similar orchestration frameworks).
Analytics Mastery: Experience leveraging web analytics data (GA4, Piwik) for behavioral modeling.
Education
Bachelors degree in Statistics, Analytics, Mathematics, Computer Science, Information Technology or related field and 4 years+ experience