Why this role

Our forecasting algorithm and time-series models are already built. What we need now is someone to make them run reliably—ingesting messy client data, maintaining our GCP/BigQuery infrastructure, and shipping outputs consistently as we scale from pilot to production. This role owns that.

Who you are

You're a Data/ML Engineer with strong software engineering instincts. You write clean Python, you're comfortable wrangling dataframes, and you know how to build pipelines that don't break at 2am.

Required

1–3 years of commercial experience in data engineering, ML engineering, or a similar role

️ Strong Python skills with hands-on pandas/dataframe experience

Experience building and running data pipelines (ETL/ELT) with orchestration tools

☁️ Familiarity with cloud platforms (GCP preferred) and tools like BigQuery

️ Comfortable working with messy, real-world data—CSV ingestion, schema validation, inconsistent formats

Able to deploy and monitor models and pipelines in production

Can build and maintain dashboards to give the team and clients real-time visibility into model health and forecast outputs

You love AI tools and use them to build shit fast—Cursor, Claude, Copilot, whatever gets the job done

Clear communicator who documents well and cares about reliability, not just shipping fast

Excited to work in a small, fast-paced startup where you'll take ownership and jump in wherever needed

Desirable

Enough statistics/ML knowledge to retrain, tune, and troubleshoot models—not just wrap APIs

️ Experience owning infrastructure: environments, dependencies, CI/CD, rollbacks

Familiarity with containerisation (Docker) or infrastructure-as-code

️ Interest in food retail, fresh food, or supply chain domains

What the job involves

Data pipelines — Build, maintain, and improve our ETL/ELT pipelines. Ingest messy client data (CSV exports, varying formats, schema mismatches) and transform it reliably for forecasting.

Production systems — Deploy statistical/ML models and keep them running at scale. Monitor pipelines and models, set up alerting for failures and data quality issues.

Visibility — Build dashboards so the team and clients can see model health and forecast outputs in real time. Surface insights when performance drifts.

Infrastructure ☁️ — Own our GCP environments, BigQuery setup, dependency management, and release processes.

Code quality ✅ — Write well-structured, tested Python with proper version control practices (branching, PRs, code review).

Client onboarding — Own the end-to-end process from receiving a client's first data extract to delivering clean forecast outputs.

Collaboration — Work closely with our Head of Data Science to run, maintain, and troubleshoot existing models. Document systems and runbooks clearly.

Team & reporting

• You'll be the first dedicated Data/ML Engineer, working directly with the founder (who loves using AI to build stuff and has a background in UX and product) as their technical sidekick. You'll also collaborate closely with our Head of Data Science and the rest of the founding team. This is a high-impact role where you'll shape how we build and scale our technology, data infrastructure from day one.