Overview

• *Hybrid Work Mode: 3days WFO/ week • *Experience Range: 6-10years in relevant domain

Qualifications

• Advanced degree (MS or PhD) in computer science, engineering, physics, statistics, mathematics, operations research, or a related quantitative field, with 6–10 years of hands-on experience in predictive modelling and data mining.
• Strong applied statistics foundations — distributions, percentiles and empirical CDFs, robust estimators, variance and dispersion measures, and hypothesis testing — applied to high-volume operational data where outliers and skew are the norm rather than the exception.
• Proven experience with a range of modelling techniques, such as neural networks, logistic regression, non-linear regression, random forests, decision trees, support vector machines, and linear/non-linear optimization.
• Practical experience with unsupervised and semi-supervised methods used where labels are scarce — clustering, density- and distance-based outlier detection, isolation forests, dimensionality reduction, autoencoders, information-theoretic measures such as entropy and divergence, and time-series or sequence modelling with calibrated anomaly scoring — along with the judgment to reach for a simpler statistic when one will do.
• Ability to take a detection problem end to end — from raw data and feature construction through model choice, scoring, thresholding, and evaluation — supported by strong programming skills (such as Java, Python, C++, or C) and hands-on Linux experience.
• Background in machine learning and AI is valued, particularly experience in cybersecurity, fraud, or other adversarial domains, and in deploying and monitoring models in production.
• Design and build detection models over large-scale behavioural and security telemetry — network, endpoint, authentication, and application event data — including problems where labelled examples are scarce, noisy, or unavailable.
• Engineer features from raw, high-volume event logs, including entity-level and time-windowed aggregations, behavioural baselining, temporal and periodicity features, and encoding of high-cardinality identifiers.
• Research and select appropriate statistical methods and computational algorithms, and justify the choice against a simpler baseline.
• Define scoring, calibration, and thresholding approaches that yield prioritized, explainable alerts for downstream analysts, and validate detection quality where complete ground truth does not exist.
• Work with large amounts of real-world data and ensure data quality throughout all stages of acquisition and processing, including collection, normalization, and transformation.
• Build and/or oversee teams building high-end analytic models for relevant problems, managing these projects under time constraints and working with other teams within FICO to enable integration and deployment of analytics software and solutions.
• Assist with model go-lives by performing production data validations and analysis of models in production.
• Support clients throughout the engagement — investigating and resolving issues through thorough analysis of model behaviour, and contributing to model construction, pre-sales, and post-implementation support.
• An inclusive culture strongly reflecting our core values: Act Like an Owner, Delight Our Customers and Earn the Respect of Others.
• The opportunity to make an impact and develop professionally by leveraging your unique strengths and participating in valuable learning experiences.
• Highly competitive compensation, benefits and rewards programs that encourage you to bring your best every day and be recognized for doing so.
• An engaging, people-first work environment offering work/life balance, employee resource groups, and social events to promote interaction and camaraderie.