Data Scientist/ Applied Data Analyst
Cellar Insights
- Calgary, Alberta, Canada
- Calgary, Alberta, Canada
About
Founded in 2023, Cellar Insights provides critical insights into perishable-crop storage—starting with potatoes. Our smart storage monitoring and early spoilage detection help growers and processors reduce their risk due to spoilage, shrink and color, and optimize movement timing across multi-site operations. Deployed across North America, the platform analyzes 1.5M+ storage datasets and monitors 300M+ lb of potatoes. Web and mobile dashboards deliver timely alerts and trend analytics; advanced analytics and AI refine predictions behind the scenes—so teams act earlier, waste less, and increase crop value.
Role Overview
We're hiring a Data Scientist / Applied Data Analyst to become part of the analytical backbone of our product team.
This role is centered on daily interrogation of data — exploring patterns, questioning results, validating behavior in real-world conditions, and pressure-testing assumptions before they turn into product decisions. You'll work at the intersection of Product and Engineering, helping us turn complex environmental and system data into insights that meaningfully shape what we build next.
Our data and engineering foundations are in place, and our ML platform is operating in production. What we're looking for now is someone who can unlock the potential inside that data — exploring it deeply, challenging interpretations, and helping the team understand what the data is truly telling us.
You'll report into Product and collaborate closely with Engineering and domain experts. This is a role for someone who wants their analysis to directly influence product direction and real-world outcomes.
What you will work on
Your work will span a range of analytical questions that support product learning and decision-making, including:
Validation and refinement: Helping validate logic and assumptions by connecting product behavior to real-world outcomes and testing ideas before they reach production.
Sensor and signal understanding: Exploring and characterizing deployed sensor signals across conditions to better understand behavior, limitations, and meaningful patterns.
System comparison and benchmarking: Analyzing and comparing internal data with integrated systems to understand differences in behavior, reliability, and data quality.
ML and event support: Conduct structured analysis and event identification that strengthens validation, supervised learning, and downstream model improvements.
Future-ready data thinking: Helping define data needs and structures that support upcoming product initiatives and reduce future constraints.
Exploratory investigation: Conducting hypothesis-driven exploration to challenge assumptions, uncover insights, and identify opportunities that inform product direction.
Technical Environment
You'll be consuming data from a GraphQL API and working with DynamoDB and flat file data sources. Our ML platform is in production; the analytics layer that connects the business and product team to that data is where you'll focus your energy and creativity.
What you bring
3-5 years of hands-on experience in a data science, applied analytics, or quantitative research role — ideally within a product or engineering environment where your work directly influenced decisions.
Python — Your primary working language for analysis, modeling, and data manipulation
SQL — Comfortable writing queries against production data stores
Time-series and sensor data — Experience working with high-frequency, real-world operational data (imperfect, noisy, and interesting)
Statistical methods — Solid grounding in hypothesis testing, regression, distribution analysis, and experimental design
Predictive analytics — Experience building and validating predictive models, not just descriptive dashboards
Visualization and communication — Ability to build and use tools like Grafana to explore data and communicate findings clearly to non-technical stakeholders
Working Style
You question assumptions reflexively — if a number looks right, you check it anyway
You're comfortable with ambiguity and evolving problem statements
You balance analytical rigor with speed and pragmatism
You build understanding before you build slides
You thrive in small teams where your work is visible and consequential
Nice to Have
Experience in AgTech, agriculture, food production, or IoT/sensor-based systems
Familiarity with AWS services (DynamoDB, S3, Lambda)
Background in applied ML or feature engineering for production models
Experience with Grafana or similar operational analytics tools
Why this role is for you
You'll have real impact, fast. In a small, focused team, your analysis won't sit in a slide deck — it will change what we build, how we deliver our products, and how we protect millions of dollars of stored crop.
The data is genuinely fascinating, and you are critical to connecting the dots. You'll work with environmental sensor data, crop storage risk signals, multi-season agricultural patterns, and cross-system integrations. This is real-world data our users make decisions from — the kind of work that makes data science rewarding.
You're joining at the right time. We have a working product, paying customers, and major processor partnerships forming. The analytics capability you build will directly support our path to building on our foundations and shaping the product for years.
The mission matters. Potato storage losses represent massive food waste and economic harm to family farming operations. The work you do here protects livelihoods, reduces food waste, and proves that precision agriculture works beyond the field.
How to Apply?
Send your application to
Include the role you're applying for in the subject line
Provide a cover letter detailing your relevant experience and why you are interested in joining Cellar Insights Inc.
Languages
- English
Notice for Users
This job comes from a TieTalent partner platform. Click "Apply Now" to submit your application directly on their site.