Senior Data Scientist (Canada)

Atreides Caseri Inc.•Calgary, AB

16d•Hybrid

About The Position

Atreides helps organizations transform large and complex multi-modal datasets into information-rich geo-spatial data subscriptions that can be used across a wide spectrum of use cases. Currently, Atreides focuses on providing high-fidelity data solutions to enable customers to derive insights quickly. Atreides transforms the chaos of petabyte-scale, all-domain data—land, air, sea, space, and cyber—into real-time operational clarity. We are a fast-moving, high-performance international scale company. We trust our team with autonomy, believing it leads to better results and job satisfaction. With a mission-driven mindset and entrepreneurial spirit, we are building something new and helping unlock the power of massive-scale data to make the world safer, stronger, and more prosperous. We are a passionate team of technologists, data scientists, and analysts with backgrounds in operational intelligence, law enforcement, large multinationals, and cybersecurity operations. We obsess about designing products that will change the way global companies, governments and nonprofits protect themselves from external threats and global adversaries. As a Senior Data Scientist at Atreides, you will lead deep analytical investigations that uncover structure, relationships, and operational insight from complex and high-volume data streams. You’ll architect workflows for pattern identification, anomaly detection, and interaction analysis across disparate data sources — often involving tracked entities, sensor feeds, or behavioral signals. You will also define and implement quality assurance methodologies that ensure analytical outputs are consistent and interpretable, collaborating closely with engineers to embed those checks in production systems. In addition, you’ll take point on high-value or urgent analytic requests from internal and external stakeholders, helping translate open-ended questions into reliable, data-driven answers.

Requirements

5+ years of experience in data science, applied analytics, machine learning, or analytical R&D.
Advanced expertise in Python and distributed compute frameworks (e.g., Spark, Databricks), including strong proficiency in Spark SQL.
Strong background in statistical inference, anomaly detection, clustering, interaction modeling, or other analytical methods suited to large and heterogeneous datasets.
Experience working with multi-source, semi-structured, geospatial, or entity-centric data, with a strong ability to derive insight from complex operational environments.
Demonstrated success building data quality, validation, or reliability frameworks, particularly for analytical workflows or model-adjacent processes.
Ability to translate ambiguous analytical problems into structured, reproducible investigation plans.
Excellent communication, mentorship, and cross-functional collaboration skills.

Nice To Haves

Experience with MLflow, feature stores, or MLOps platforms; familiarity with model lifecycle management, reproducibility tooling, or production model monitoring.

Responsibilities

Design and lead investigations into patterns, trends, and edge cases across filtered datasets.
Develop interaction models and fused analyses across multiple entity types and data modalities.
Design data validation, anomaly sanity checks, and analytical reliability frameworks to ensure analytical outputs behave correctly across varied data inputs.
Partner with solutions and data engineering to embed analytic logic into data pipelines and services.
Conduct bespoke, high-complexity analysis in support of customer-facing or operational needs.
Guide team best practices in Spark SQL usage, data documentation, and exploratory reproducibility.