Staff Machine Learning Engineer

Want to help us help others? We’re hiring! GoFundMe is the world’s most powerful community for good, dedicated to helping people help each other. By uniting individuals and nonprofits in one place, GoFundMe makes it easy and safe for people to ask for help and support causes – for themselves and each other. Together, our community has raised more than $40 billion since 2010. Join GoFundMe as our next Staff Machine Learning Engineer (Pricing). In this role, you will design, develop, and deploy machine learning systems that power pricing and monetization programs across GoFundMe such as personalized donation and checkout experiences, donation yield optimization (one-time and recurring), recurring donor LTV optimization, fundraising goal suggestions, and more. This role requires strong end-to-end execution and deep expertise in building production ML systems (data → training → online inference → measurement) with rigorous experimentation and monitoring. This is a hybrid position. Candidates considered for this role will be located in Buenos Aires, Argentina. The Job… Own end-to-end ML systems for pricing optimization, from problem framing and metric definition (e.g., donation yield, conversion, retention, LTV) to model development, launch, and iteration in production. Design and implement backend model pipelines including feature engineering, training, and evaluation. Build low-latency real-time inferencing services, including API design, caching strategies, model packaging, and deployment on Kubernetes. Collaborate with teams to develop instrumentation and event pipelines to capture user and campaign activity required for training and evaluation (e.g., impression/click/submit, donation amount, tip amount, recurring enrollment/cancellation), ensuring schema quality, lineage, and privacy-by-design. Apply causal and experimental methodologies to measure impact and avoid biased optimization, including online A/B testing design, guardrail metrics, sequential testing considerations, and counterfactual/causal approaches when needed. Develop optimization approaches appropriate for pricing-like problems, such as uplift modeling, bandits, constrained optimization, calibration, and multi-objective tradeoffs (e.g., yield vs. donor trust, short-term conversion vs. long-term retention). Establish ML operational excellence by implementing model observability (latency, errors, drift, calibration, business KPI deltas), automated retraining triggers, rollback strategies, and incident response playbooks for pricing systems. Partner cross-functionally with Product, Engineering, Design, and Legal/Privacy stakeholders to translate business goals into measurable technical deliverables and ship safely. Mentor and set technical direction for other engineers and scientists through design reviews, architecture decisions, and shared best practices for production ML in monetization. Employ a diverse set of tools and platforms, including Python, AWS, Databricks, Docker, Kubernetes, FastAPI, Terraform, Snowflake, and GitHub, to develop, deploy, and maintain scalable and robust machine learning systems. (Full-stack experience—e.g., integrating with web clients and experimentation frameworks—is a plus.) You… 7+ years of hands-on experience building and shipping production machine learning systems, with demonstrated ownership of backend services and ML pipelines in a high-availability environment. Strong proficiency in Python and ML libraries/frameworks such as PyTorch, TensorFlow, Scikit-learn, plus strong software engineering fundamentals (testing, code review, CI/CD, API design, performance, and reliability). Demonstrated experience in pricing/monetization or growth optimization domains preferred. Experience designing and deploying real-time model serving (sub-100ms to low-hundreds ms latency targets), including containerization, scalable inference, feature retrieval, and safe rollout strategies (canaries, shadowing, backward-compatible sch ... (truncated, view full listing at source)