Job Title

Staff Machine Learning Engineer for credit origination Join to apply for the Staff Machine Learning Engineer for credit origination role at Aviva About Aviva We are a Mexico City-based technology startup taking a unique approach to unsecured credit for underserved communities. Aviva’s physical onboarding kiosks bridge the gap for individuals living in remote areas, offering a document-free, 5-minute video onboarding process for those seeking liquidity. This asset-light acquisition strategy, combined with a superior risk model powered by computer vision and natural language processing, enables Aviva to provide the lowest interest rates available to underserved populations today. Origination Decisions at Aviva Traditional banks classify customers into risk buckets and offer fixed loan parameters. In contrast, we model: The decisions we could take now and later, such as offering larger loans after successful repayment. The probabilities of external events: customer acceptance, repayment, second loans, referrals. This results in a decision tree scoring each scenario based on profit and customer outcomes, selecting the optimal decision. Your Role at Aviva We seek a ML engineer to design new decision tree models, simulate decisions and stochastic events, define relevant datasets, train ML models, and collaborate with engineers on API modifications. Potential Projects Optimizing onboarding costs by early rejection models. Predicting collection costs for different client behaviors. Expanding and optimizing loan options. Implementing adaptive offers to improve acceptance. Modeling early repayment impacts. Rapid adaptation to macroeconomic shifts. Requirements Master's in CS, Math, or related field. 6+ years professional experience. Fluent in Spanish and English. Proficiency in Python, emphasizing clean, maintainable code. Familiarity with git. Strong analytical skills. Proactive communication. Willingness to innovate and push boundaries. Nice-to-Have Experience in finance. Neural network design for unusual data types. Reinforcement Learning experience. Knowledge of LightGBM, DVC, Pants, FastAPI, Docker, GitHub Actions, TrueFoundry, Dagster. Benefits Competitive compensation, including stock options. Growth opportunities in a fast-paced environment. 15 vacation days + 7 personal days annually. Option for remote work 3-4 days/week or fully remote (must visit CDMX twice a year). Flexible schedule. #J-18808-Ljbffr