Kpler

2 weeks ago

Data Scientist

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 13 hours agoStatus: Live

Job Summary

Own the feature engineering and experimentation roadmap behind production ML models for Product Estimation and Destination Forecast/ETA across LNG, DRY, LPG, and LIQUIDS. Build dbt features orchestrated with Airflow, run structured experiments with the kpler-ml framework tracked in MLflow, and validate improvements against a parallel baseline before promotion. Collaborate with Commodities Market Analysts and stakeholders, and help set up drift monitoring using PSI/KS thresholds for PE and DF.

Location: London

Workplace: Hybrid

Employment Type: Full time

Job Function: Data Science & Machine Learning

Seniority: Mid level

Key Responsibilities

•Own the feature engineering roadmap for ETA and Destination Forecast across all four commodity types, proposing and implementing new features as dbt models orchestrated with Airflow.
•Design and run structured experiments using the kpler-ml framework, logging runs through train, evaluation, and MLflow, and producing comparison reports versus the production baseline.
•Collaborate with Commodities Market Analysts and product stakeholders to identify where prediction quality matters most and to prioritize the experiment backlog.
•Contribute to drift monitoring by validating PSI/KS thresholds using MLflow against historical inference batches and defining meaningful drift signals for PE and DF.
•Document experiment decisions in MLflow and Confluence, treating experiment history as a first-class artifact.

Key Requirements

•2+ years applying ML to real-world production problems with models running in production with real consequences for errors.
•Experience with geospatial or sequential data (e.g., vessel trajectories, routing patterns, H3/S2 grid systems or equivalent).
•Python proficiency sufficient to implement new features, write dbt models, and script experiments (not just use notebooks).
•Familiarity with MLflow or equivalent experiment tracking (Weights & Biases, Neptune, etc.).
•Familiarity with Redshift or other columnar warehouses for large-scale feature queries and dbt (authoring or reading SQL models).

Experience:2+ yearsProduction machine learning

Tech Stack:PythonDbtAirflowKpler-ml frameworkMLflowWeights & BiasesNeptuneH3S2RedshiftSQLAISConfluenceMLFlow

Company Brief

Kpler

Provides real-time commodity, shipping and trade intelligence combining satellite, AIS, customs and market data to deliver analytics for energy, dry bulk, petrochemicals, metals and agricultural markets, enabling trading, risk management and market transparency.

Industry: Data Infrastructure

Company Size: Large (251 to 1,000 employees)

Growth: Scaleup

Headquarters: Paris, France

Founded: 2014

Website LinkedIn

Loading job details...

Preparing the role view and application actions.

Kpler

2 weeks ago

Data Scientist

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 13 hours agoStatus: Live

Job Summary

Location: London

Workplace: Hybrid

Employment Type: Full time

Job Function: Data Science & Machine Learning

Seniority: Mid level

Key Responsibilities

•Own the feature engineering roadmap for ETA and Destination Forecast across all four commodity types, proposing and implementing new features as dbt models orchestrated with Airflow.
•Design and run structured experiments using the kpler-ml framework, logging runs through train, evaluation, and MLflow, and producing comparison reports versus the production baseline.
•Collaborate with Commodities Market Analysts and product stakeholders to identify where prediction quality matters most and to prioritize the experiment backlog.
•Contribute to drift monitoring by validating PSI/KS thresholds using MLflow against historical inference batches and defining meaningful drift signals for PE and DF.
•Document experiment decisions in MLflow and Confluence, treating experiment history as a first-class artifact.

Key Requirements

•2+ years applying ML to real-world production problems with models running in production with real consequences for errors.
•Experience with geospatial or sequential data (e.g., vessel trajectories, routing patterns, H3/S2 grid systems or equivalent).
•Python proficiency sufficient to implement new features, write dbt models, and script experiments (not just use notebooks).
•Familiarity with MLflow or equivalent experiment tracking (Weights & Biases, Neptune, etc.).
•Familiarity with Redshift or other columnar warehouses for large-scale feature queries and dbt (authoring or reading SQL models).

Experience:2+ yearsProduction machine learning

Tech Stack:PythonDbtAirflowKpler-ml frameworkMLflowWeights & BiasesNeptuneH3S2RedshiftSQLAISConfluenceMLFlow

Company Brief

Kpler

Industry: Data Infrastructure

Company Size: Large (251 to 1,000 employees)

Growth: Scaleup

Headquarters: Paris, France

Founded: 2014

Website LinkedIn