Sr. Data Scientist

Sr. Data Scientist

Position Type: Full Time

Location: Toronto, ON (remote-hybrid)

Employer Description

Eneon is a leading Battery Energy Storage System (BESS) company and one of the fastest growing in the renewable energy and energy management industries. We are a tight-knit team of seasoned professionals who engineer, integrate, and operate premium BESS solutions across North America.

Eneon is an opportunity to hit the ground running with a growing organization, to be a part of its growth, and to help drive the global energy transformation at large. Eneon is also an equal opportunity employer. We celebrate diversity and are committed to creating an inclusive environment for all employees. We believe diverse teams and diverse perspectives lead to better outcomes and breakthrough thinking, which are differentiators in any business and fundamental to our long-term success.

Position Description

The Sr. Data Scientist will be responsible for transforming Eneon’s operational telemetry into reliable, actionable data systems that support decision-making across the company. As Eneon’s first data scientist, this position will define the company’s data strategy, owning the full lifecycle from raw operational data through analysis, modeling, and deployment into production data systems. This role spans both data science and data engineering.

Key responsibilities include:

Data Strategy & Architecture

• Define and own Eneon’s operational telemetry data strategy, from raw historian data to curated analytical datasets
• Set data resolution, aggregation/downsampling, and retention approaches appropriate for analytics and reporting
• Design retention policies balancing analytical value, OEM/warranty requirements, cost, and accessibility
• Establish analytical schemas and standards so telemetry is interpretable, trustworthy, and consistently modeled

Data Engineering & Pipeline Development

• Design, build, and maintain pipelines from production historian systems to analytical data stores
• Own the transformation layer, ensuring logic is explicit, reviewable, and production-ready
• Keep pipelines documented, version-controlled, reproducible, and maintainable by others

Applied Data Science & Modeling

• Lead end-to-end data science work (preprocessing, EDA, feature engineering, model development, training, and evaluation)
• Develop predictive models for reliability use cases (e.g., predictive maintenance and failure-risk reduction)
• Apply sound methods to fleet performance, diagnostics, degradation, anomaly detection, and forecasting problems
• Build proof-of-concepts to validate feasibility and value before scaling

Production & Operation

• Deploy models and analytical systems into production environments for inference, reporting, and logging
• Define and document model inputs, outputs, assumptions, limitations, and failure modes
• Design analytical systems for long-term operation, handoff, and ownership beyond a single contributor

Cross-Functional Collaboration & Enablement

• Collaborate with SCADA & OT engineers on data capture, tagging, historian configuration, and data models that enable analytics
• Partner with engineering, product, architecture, and operations teams to translate system data into insights and decisions
• Support design and validation of customer-facing metrics/KPIs that are accurate, meaningful, and actionable
• Communicate methods and results (including limitations) to technical and non-technical stakeholders

Governance & Quality

• Ensure analytical pipelines, models, and datasets adhere to internal standards for quality, documentation, and maintainability
• Promote explainable, transparent methods suitable for review and use by engineers and other stakeholders

Required Qualifications

• 8 to 15 years of applied experience in data science, data engineering, or quantitative analytics working with operational data from physical systems
• A Bachelor’s degree in a quantitative discipline (statistics, mathematics, physics, computer science, engineering, or equivalent). A Master’s degree or Ph.D. is preferred
• Deep experience with time series data from physical assets: high-frequency, small-packet-size sensor data with the associated realities of noise, missing data, communications dropouts, and sensor drift
• Strong proficiency with time series databases (e.g., InfluxDB, TimescaleDB, historian-native storage such as OSIsoft PI or similar) including schema design, query optimization, and retention policy implementation
• Proficiency in Python for data analysis, modeling, and pipeline development
• Experience with SQL and relational databases for structured data retrieval and integration
• Practical experience building data transformation pipelines and moving raw operational data into curated, queryable analytical datasets
• Experience designing data retention and downsampling strategies for high-volume operational data
• Experience building, validating, and deploying predictive models on real-world operational data, not only curated academic datasets
• Ability to work independently under ambiguous requirements with minimal supervision
• Strong communication skills with the ability to translate analytical findings into clear recommendations for both technical and business audiences
• Professional maturity and judgment to exercise technical authority responsibly as the company’s sole data science practitioner

Assets

• Experience in energy storage, power systems, renewable energy, or utility-scale infrastructure
• Experience with predictive maintenance or condition-based monitoring in industrial or fleet operations environments
• Familiarity with battery degradation modeling, state-of-health estimation, or electrochemical system analytics
• Experience with industrial data environments: OPC-UA, MQTT, Modbus, or SCADA-adjacent data sources
• Background in process manufacturing, oil & gas, fleet operations, or other domains with high-frequency physical asset data
• Experience with cloud-based analytics platforms (Azure, AWS, or GCP) for time series workloads
• Familiarity with data visualization tools (Grafana, Plotly, or similar) for operational data exploration
• Experience with statistical process control, anomaly detection, or change-point detection on streaming data
• Exposure to ISA-88/95 data modeling concepts or Unified Namespace architectures
• Experience operationalizing ML models in production environments — model deployment, monitoring, retraining pipelines
• Familiarity with Git, CI/CD, and software engineering practices applied to data science workflows

A note on the use of AI in our hiring process: We use AI-enabled tools to help sort and assess applications against core job-related criteria (such as skills, experience, and qualifications). AI does not make hiring decisions. The members of our hiring team review results carefully and make all final decisions. Your application materials are used only for the purpose of evaluating your candidacy for this role.

Finally, a note on qualifications: Even if you don't have every listed requirement, but you feel strongly about this role and believe you'd bring value, we encourage you to apply. We'd rather hear from someone who's genuinely excited about the work than miss out because they didn't tick every box!

Thank you for your interest in a career at Eneon!