Data Scientist

Summary

The position of Data Scientist is for the Logicpath division within Loomis.

We are a team of tech-savvy cash inventory management experts passionate about helping financial institutions succeed.

We provide a collaborative and supportive environment that values the participation and contribution of all employees.

We are looking for people who want to be challenged, solve complex problems, and feel connected to a larger purpose.

Our mission-focused team, collaborative nature, and commitment lead dedication to client results.

Function

The Data Scientist will play a critical role in designing, scaling, and operationalizing advanced analytics and machine learning solutions across the company's FinTech platforms.

This role will lead complex forecasting initiatives, develop AI-driven use cases (including LLM-enabled support tools), and establish strong data quality and model governance practices.

This position requires a hands-on technical leader who can translate real-world operational and financial problems into robust, production-ready data science solutions, while partnering closely with engineering, product, implementation, and client-facing teams.

The ideal candidate combines strong statistical and machine learning expertise with practical engineering ability and a track record of delivering production-grade solutions in environments where communication, business processes, data quality, and operational constraints matter as much as model performance.

This very technical person is capable of thinking in terms of "problem -> solution -> product -> value", not just "models".

Key Responsibilities

Forecasting & Advanced Analytics



* Lead the design, development, and optimization of forecasting models for:

o Cash demand (branches, ATMs, retail locations, vaults)

o Labor and operational workload forecasting



* Apply and evaluate time-series, probabilistic, and machine-learning techniques to improve forecast accuracy and stability.



* Own model performance monitoring, drift detection, recalibration strategies, and continuous improvement.

AI, ML, & LLM Enablement



* Design and implement LLM-based use cases to support internal teams (e.g., support, implementation, operations).



* Develop approaches for prompt engineering, evaluation, and governance of LLM outputs.



* Partner with engineering to integrate AI capabilities into production SaaS workflows.



* Define metrics to measure effectiveness, accuracy, and operational impact (ROI) of AI solutions.

Data Quality, Governance & Model Risk


* Establish data quality frameworks to detect anomalies, gaps, and integrity issues across large transactional datasets.


* Define validation rules, thresholds, and scoring mechanisms to support data confidence and forecast reliability.


* Contribute to model documentation, explainability, and governance practices aligned with financial services expectations.


* Support audit, compliance, and client ...