Data Scientist - Predictive Modeling & Supply Chain Analytics

Clevertech Partners, LLC
New York, NY, United States
12 days ago

Role details

Contract type
Permanent contract
Employment type
Full-time (> 32 hours)
Experience level
Expert
Experience required
5 years minimum
Working hours
Regular working hours
Languages
English
Job source

Tech stack

Data Analysis Data Transformation Apache Hive Python (Programming Language) SAP ERP SAP (Applications) SQL Databases Transaction Data Pandas Pyspark Scikit Learn Statistics Packages
+2 more
Software Version Control Databricks

Job description

  • Build demand forecasting models using time-series methods appropriate to supply chain variability-applying CV-based segmentation to classify materials by demand pattern and selecting the right forecasting approach per segment (e.g., smooth, erratic, lumpy, intermittent).
  • Perform demand variability analysis across material master and movement data-quantifying forecast error, identifying root causes of variability, and producing inputs that planning teams can act on directly in SAP.
  • Develop inventory pre-positioning and health/trend monitoring (HTMS) analytics, translating model outputs into actionable signals for supply chain planners-including safety stock recommendations, reorder point adjustments, and MRP parameter tuning.
  • Work directly with SAP ECC planning data-extracting and interpreting MD07 exception messages, purchase requisitions vs. PO receipts, and MRP-generated signals to understand how planners currently work and where predictive models create the most value.
  • Partner with cross-functional teams-supply chain planners, procurement, and operations-to translate domain knowledge into concrete model inputs, validate outputs against real planning decisions, and communicate findings in terms the business understands.
  • Perform exploratory data analysis (EDA) on SAP transactional data (MARC, MARD, EKKO/EKPO, purchase reqs) to uncover demand patterns, supply variability, and leading indicators that inform forecasting and inventory models.
  • Build and maintain analytical workflows in Databricks using PySpark, SQL, and Notebooks-ensuring reproducibility, version control, and handoff-readiness for engineering and downstream consumers.
  • Establish modeling best practices for validation, segmentation logic, and presentation of findings-ensuring models are interpretable and trusted by both technical teams and supply chain planners who act on the outputs., This is a fully remote position; however, candidates must be based in regions that align with the Pacific, Central, or Eastern U.S. time zones to ensure effective collaboration with client and team schedules.

Requirements

We’re seeking an experienced Data Scientist with a strong applied statistics background and deep supply chain domain knowledge to join an enterprise manufacturing client., * 5+ years in a Data Scientist or analytical role, with hands-on experience building statistical models in supply chain, manufacturing, or industrial planning contexts.

  • Strong foundation in applied statistics-time-series forecasting fundamentals (ARIMA, exponential smoothing, intermittent demand models), demand variability analysis, and CV-based material segmentation. Classical statistical rigor is valued over black-box ML here.
  • Working understanding of supply chain planning concepts-MRP logic, purchase requisitions vs. PO receipts, safety stock, reorder points, and how planners make decisions-sufficient to translate planning requirements into model design.
  • Hands-on experience with Databricks for analytical model development-PySpark and Spark SQL for data transformation and aggregation, and Notebooks for reproducible analysis and model iteration.
  • Strong proficiency in Python (scikit-learn, statsmodels, pandas) for modeling and SQL for extracting and manipulating large SAP transactional datasets.
  • Ability to present model outputs and analytical findings to both technical teams and non-technical supply chain stakeholders-translating statistical outputs into planning-relevant language.
  • Strong written and verbal communication skills in English.

About the company

At Lumenalta, we partner with forward-thinking organizations to build technology solutions that scale, delight users, and accelerate business growth. Our global teams bring curiosity, commitment, and technical excellence to every project. We value transparency, autonomy, and impact-empowering every team member to do their best work., Why Lumenalta is an amazing place to work at

At Lumenalta, you can expect that you will:

  • Be 100% dedicated to one project at a time so that you can innovate and grow.
  • Be a part of a team of talented and friendly senior-level developers.
  • Work on projects that allow you to use leading tech.

Apply for this position

This job is hosted externally. Click below to view the full posting and apply.

Apply on arc.dev

Good distractions

Talks and stories from around this role — technically off-topic, practically not.

2:03 min

Accelerating pandas dataframes using cudf module plugins

Ankit Patel Ankit Patel · World Congress 2024

4:32 min

Harnessing Spark with Python using PySpark and Py4J

Ayon Roy · LIVE

1:34 min

Bringing diverse skills to industrial data science roles

Katja Träumner

6:58 min

Analyzing production code coverage data using pandas

Markus Harrer Markus Harrer · World Congress 2021

2:44 min

Integrating data analytics into the talent acquisition function

Kobi Kobi +1 · World Congress 2025

3:37 min

Scaling machine learning pipelines from prototypes to petabytes

Julian Joseph · LIVE

Videos

See all

Related articles

See all