Senior ML-Engineer, Finance

Highlights: Role: Senior ML-Engineer, Finance Location: Spain, Remote Language: Strong English required (C1) About Us Fundraise Up is a modern fundraising platform built to make donating to nonprofits as fast and convenient as possible. We continuously innovate to reduce page load times, boost conversion rates, and support a wide range of payment methods. Each month, people around the world contribute tens of millions of dollars through our platform. The world’s leading nonprofit organizations trust Fundraise Up. UNICEF, the most prominent UN charity, uses our platform for 100% of its online fundraising. So does the American Heart Association, the Alzheimer’s Association, and many others. We’re proud to maintain a 4.9 out of 5 rating on leading review platforms. We serve the enterprise segment, with a primary client base in the US, Canada, UK, and Australia. The Team Our product development team is currently at 150+ and growing. Team members are located across Spain, Serbia, Poland, Portugal, Turkey, Cyprus, Georgia and Armenia. We primarily communicate in Russian. We’re a tight-knit, high-impact team where every task matters. It’s a dynamic, collaborative environment where smart, curious engineers support one another, share knowledge, and strive for excellence. We encourage open dialogue and host bi-weekly engineering meetups to explore technical topics and showcase team insights. About the Role We're looking for an ML Engineer with 5+ years of production experience to own a high-impact client intelligence initiative. Following a successful proof-of-concept with an external consultant, we are bringing this project fully in-house. The ultimate goal is to generate a comprehensive, enriched list of all potential clients globally — understanding their product requirements, industry verticals, and overall revenue potential — and deploy a scoring model that feeds directly into our sales pipeline. This is an end-to-end ownership role. You will build from the ground up: data collection, enrichment, modeling, and production deployment. The project is co-managed by company executives and has a high strategic value. What You’ll Do Build a market intelligence data-base via collecting different types of data (scraping, enrichment), fixing data pipeline and creating an ML model for scoring and analysis of the raw data. Design and operate scrapers to extract key signals from nonprofit websites, including products used, payment tools, and industry vertical indicators. Develop critical filters such as an "Is this website for fundraising?" binary classifier, alongside other features that distinguish high-potential prospects. Source and integrate financial data from international nonprofit registries, as well as third-party signals from SimilarWeb and Facebook. Store and structure the enriched dataset in our internal database, making it accessible and useful across the broader team for research and analysis. Work closely with the sales team to understand their qualification criteria. Analyze disqualified accounts in Salesforce to identify common exclusion patterns and refine scoring accordingly. Deploy the scoring model and own the process of integrating outputs into Salesforce in a clean, maintainable way. Build a scraper to monitor existing clients' websites, tracking whether Fundraise Up tools are correctly implemented across their properties. Challenges You'll Navigate At the scale of ~1 million domains, expect domain duplicates, inconsistent data, and significant noise. You'll need to develop robust, cost-efficient filtering pipelines. A single model won't cover everything — you'll likely build several targeted sub-models tailored to specific verticals and geographies as the project matures. All of this needs to be accomplished without incurring high infrastructure or data costs. Pragmatic, scrappy solutions are valued here. Requirements 5+ years of ML/DS experience solving real product problems Strong expertise in ML and mathematical statistics: solid knowledge of classical algorithms (especially gradient boosting) and understanding of modern NLP/LLM approaches Proven experience with large-scale web scraping and data pipeline construction Metrics-driven mindset: ability to connect ML metrics (ROC-AUC, F1, RMSE) with business metrics (conversion rate, LTV) Strong engineering culture: confident in Python with a product-oriented approach; we value clean code, knowledge of design patterns, and solid engineering practices Advanced SQL; ability to independently build complex datasets in ClickHouse and work with MongoDB MLOps understanding: hands-on experience with experiment tracking and production workflows (Docker, Git, CI/CD) Autonomy: ability to break down ambiguous problems, choose the right tech stack, and deliver to production Our Tech Stack Core: Python (uv, ruff), FastAPI, Pydantic, Docker Models: CatBoost, Uplift Modeling (CausalML), OpenAI (RAG, Prompt-Engineering) Data: ClickHouse, MongoDB, pandas, Polars, Redis