AI Engineer

Calling all innovators - find your future at Fiserv.

We're Fiserv, a global leader in Fintech and payments, and we move money and information in a way that moves the world. We connect financial institutions, corporations, merchants and consumers to one another millions of times a day - quickly, reliably, and securely. Any time you swipe your credit card, pay through a mobile app, or withdraw money from the bank, we're involved.

If you want to make an impact on a global scale, come make a difference at Fiserv.

Job Title

AI Engineer

About your role:

As an AI Engineer you will apply advanced machine learning and statistical techniques to detect, prevent, and respond to cyber threats. You will work closely with cybersecurity engineers, threat analysts, and infrastructure teams to transform large-scale security telemetry into actionable insights that protect client data and critical systems. You will help us continuously strengthen our security posture and inform risk-based decisions across the organization.

What you'll do:

* Design, build, and deploy machine learning and statistical models for threat detection, anomaly detection, fraud identification, and risk scoring using security event and telemetry data.

* Engineer robust security data pipelines, including data ingestion, cleansing, feature engineering, and model monitoring, using structured and unstructured cyber data sources (e.g., logs, alerts, network flows, endpoint data).

* Analyze outputs from security tools and platforms to identify control gaps, policy deviations, and emerging threat patterns, and translate findings into prioritized remediation recommendations.

* Partner with cybersecurity engineering, Security Operations Center (SOC), and infrastructure teams to embed AI and advanced analytics into security controls, playbooks, and incident response workflows.

* Conduct model performance evaluations, bias and drift analysis, and continuous tuning to improve detection efficacy while minimizing false positives.

* Develop clear, consumable visualizations and storytelling artifacts that communicate complex analytic findings and risk scenarios to technical and non-technical stakeholders.

* Create and maintain documentation for data sources, model architectures, assumptions, validation approaches, and deployment processes in line with internal governance standards.

Experience you'll need to have:

* 6+ years of experience in data science or machine learning using programming languages such as Python or R to build and deploy models in production environments, preferably in cybersecurity, fraud, or risk domains.

* 4+ years of experience working with security-relevant datasets and tools (for example, Security Information and Event Management platforms, endpoint protection, identity and access data, or network telemetry) in an enterprise environment.

* 4+ years of experience with SQL and one or more big data or cloud analytics platforms (for example, Hadoop, Spark, Databricks, or cloud-native services) to process large-scale security or operational datasets.

* 4+ years of experience applying machine learning methods (such as classification, clustering, anomaly detection, or time series) and model evaluation techniques to real-world problems.

* Demonstrated experience translating ambiguous business and security problems into analytic questions, framing hypotheses, and delivering measurable outcomes based on data-driven insights.

* Bachelor's degree or higher in Computer Science, Data Science, Statistics, Engineering, Cybersecurity, or a related quantitative field or equivalent combination of education, related experience and/or military experience.

Experience that would be great to have:

* Experience applying AI or advanced analytics to cybersecurity use cases such as insider threat, identity and access risk, data loss prevention, or cloud security posture management.

* Experience in the financial services or payments industry working with sensitive data and stringent regulatory or compliance requirements.

* Experience with MLOps practices and tooling (for example, CI/CD for models, model registries, feature stores, or automated monitoring) in a regulated…