Responsibilities

• Own and manage the backlog for ML-driven biometric and document verification capabilities.
• Translate fraud, identity, and customer requirements into clear and actionable ML work items.
• Partner closely with ML engineers and data scientists to refine problem statements into feasible deliverables.
• Define acceptance criteria that reflect real world performance, not just offline model metrics.
• Serve as the primary product owner for ML and data science teams.
• Participate actively in model design discussions, prioritization, and tradeoff analysis.
• Challenge scope, timelines, and modeling approaches when misaligned with business or risk objectives.
• Propose alternate ideas across data strategy, modeling approaches, workflow design, or deployment patterns.
• Support model lifecycle activities including training, evaluation, deployment, and retraining.
• Ensure monitoring, drift detection, and feedback loops are incorporated into delivery plans.
• Help define rollout, experimentation, and rollback guardrails.
• Partner with agent operations and data teams on labeling strategy and data quality.
• Help define labeling schemas and workflows to support effective model training.
• Identify risks related to label noise, bias, or insufficient coverage across geographies and document types.
• Incorporate fraud patterns and adversarial thinking into backlog prioritization.
• Ensure features and models are resilient to evolving attack vectors such as spoofs, deepfakes, and injection attacks.
• Support layered and defense in depth approaches rather than single model dependency.
• Work closely with engineering, fraud, compliance, legal, and customer teams.
• Support internal and external conversations where ML behavior or performance needs explanation.
• Translate technical constraints into clear delivery expectations for non technical stakeholders.

Requirements

• Seven or more years of experience in product ownership, product management, or equivalent delivery focused roles.
• Demonstrated experience supporting ML based products in production.
• Direct experience working with data science and ML engineering teams.
• Strong working knowledge of computer vision and ML fundamentals.
• Experience with biometric technologies such as face matching, liveness detection, and spoof prevention.
• Experience with document verification, document classification, or document fraud detection.
• Hands-on experience building ML based products in the biometric and document identity space is highly valuable.
• Ability to evaluate tradeoffs between different modeling and data approaches without being a data scientist.
• Comfortable pushing back on ML teams when solutions are over engineered, misaligned, or not production ready.
• Able to propose alternate approaches grounded in data availability, fraud realities, and delivery constraints.
• Strong attention to detail and a bias toward shipping reliable and measurable capabilities.
• Able to clearly articulate ML concepts, risks, and tradeoffs to non technical stakeholders.
• Comfortable supporting customer facing or internal discussions around model behavior and limitations.
• Able to document requirements and acceptance criteria with precision.

Preferred Experience

• Hands on experience shipping biometric or document based ML solutions into production.
• Experience in fraud, identity, or regulated environments such as financial services or fintech.
• Familiarity with model monitoring, drift management, and feedback loops.
• Experience working with global document types and jurisdictional variation.

What We Offer

• Work with a global leader in Digital Identity and Fraud prevention.
• Build products that power secure, seamless digital experiences.
• High-impact role in a fast-growing market.
• Excellent working atmosphere and great culture.
• 100% remote-friendly (with optional work from our Barcelona office in Sant Cugat).
• Work with a diverse global team passionate about technology and impact.
• Continuous learning and growth opportunities.