Data Scientist

About HazTrack

HazTrack is revolutionizing the used cooking oil (UCO) collection sector with innovative IoT sensor technology and live data analysis. This industrial segment plays a key role in the circular economy by transforming restaurant waste into renewable biofuels, yet faces challenges such as inefficient routing, expensive emergency pickups, and significant losses due to UCO theft. Our rugged wireless tank-level sensors linked to a robust software platform provide real-time asset visibility, helping collectors streamline routes, cut operational expenses, prevent theft, and utilize data-driven insights. We are a rapidly expanding, venture-backed startup headquartered in Calgary, expanding across North America to become the core platform for UCO collection operations.

Role Overview

We seek a hands-on Data Scientist to take full ownership of our existing data function. You will refine and enhance our current signal processing pipelines, built with Python and pandas under CI/CD standards, while championing high data quality and best practices as our team grows. Collaborating closely with engineering, you will ensure robust data standards and reliable results.

Responsibilities

• Manage and improve our signal processing pipeline, enhancing filtering and smoothing techniques to clean noisy sensor data, strengthening event detection algorithms for fills, dumps, theft, and malfunctions, and refining predictive models forecasting tank levels and disposal times.
• Oversee data pipeline standards encompassing ingestion, transformation, and tagging of sensor data from devices in the field, continuously optimizing for scalability.
• Maintain and upgrade data visualization dashboards and internal tools to provide clear, actionable insights for both product development and operational decision-making, as well as customer reporting where applicable.
• Promote and enforce data and coding standards, ensuring quality as the company scales sensor deployments, customer base, and data team size.
• Collaborate cross-functionally with hardware, firmware, and engineering teams to interpret sensor behavior accurately and convert raw signals into valuable customer insights.

Qualifications

• Proven expertise with signal processing techniques including filtering, smoothing, event or anomaly detection, and forecasting on real-world noisy sensor or time-series datasets using Python and pandas.
• Strong ownership mindset for data quality and best practices, with the ability to uphold high standards amid rapid growth.
• Comfortable handling end-to-end data workflows: ingestion, transformation, tagging, analysis, and visualization, with the ability to work autonomously and coordinate with engineers.
• Solid foundation in statistics and applied mathematics related to time-series and sensor data.
• Fluency in SQL and experience interacting directly with databases and structured datasets.
• Willingness and ability to work onsite in Calgary, Alberta, Canada.

Preferred Additional Skills

• Experience designing and managing ETL pipelines with tools like Airflow or dbt.
• Familiarity with data lakes or warehouse technologies such as Snowflake, BigQuery, Redshift, or S3-based storage.
• Exposure to business intelligence and data visualization platforms like Metabase, Grafana, Tableau, Power BI, or Looker.
• Background with time-of-flight or ranging sensors such as Lidar or Radar.
• Experience working with IoT or industrial sensor data directly from field hardware.
• Knowledge of cloud data infrastructure including AWS, GCP, or Azure environments.

What We Offer

This role offers high ownership in advancing an established data capability with strong engineering backing and direct access to company leadership. You'll influence company scaling strategies within a fast-growing, well-funded startup serving a significant market. Compensation is competitive, tailored to your experience, and includes equity and benefits.