Latest AI JobsBrowse Jobs
impact.com logo

Senior Data Scientist, Product Data

impact.comCape TownProduct
Apply on company site
Salary
Not listed
Job type
Full-time
Posted
13 Feb 2026
Status
Open · checked 7d ago

About this role

The Senior Data Scientist, Product Data position at impact.com in Cape Town focuses on managing the analytical and technical foundation of product data quality across a global commerce ecosystem. This role suits an experienced data scientist with strong software engineering skills who enjoys tackling complex catalog hygiene, entity resolution, and search infrastructure challenges.

Role Overview

In this position, the professional oversees catalog hygiene, transaction matching, classification modeling, deduplication, and global product identity. Working across structured catalogs and large-scale sales transaction universes, the specialist builds models and infrastructure that directly power search, recommendations, and business intelligence. Responsibilities include taking models from research to production, building scalable data pipelines, and establishing monitoring systems to ensure product data remains trustworthy and continuously improving.

Key Responsibilities

Build, deploy, and maintain machine learning models for automated product categorization and taxonomy assignment across hierarchical category structures.
Conduct deep-dive analyses into catalog completeness and correctness, and own data quality analytics for the sales transaction universe.
Assess Global Product ID coverage and build matching algorithms to link sales transactions to catalog products.
Identify product variants and duplicates using clustering, entity resolution, embeddings, and similarity-based techniques.
Build and maintain product graph infrastructure that captures relationships between products, variants, brands, categories, retailers, and transactions.
Take models and analytics prototypes from proof of concept to production, owning deployment, testing, monitoring, and iteration.

Requirements

Minimum of 5 years of experience in data science, machine learning engineering, or analytics engineering.
At least 2 years focused specifically on product data, catalog quality, entity resolution, search, retrieval, or e-commerce analytics.
Proven ability to build production-grade data pipelines and independently deploy machine learning models with strong software engineering fundamentals.
Demonstrated experience analyzing and improving large-scale structured data quality.
Track record of building and deploying classification models, ranking systems, or search and retrieval pipelines in production.
Bachelor's degree in a quantitative field such as Computer Science, Statistics, Mathematics, or Engineering.

Nice to Have

Experience with vector search, embeddings, and vector databases like FAISS, Pinecone, Weaviate, or Milvus.
Familiarity with search and retrieval systems such as Elasticsearch, Solr, or BM25.
Experience with graph databases and graph analytics like Neo4j or NetworkX.
Knowledge of natural language processing techniques tailored for product data.
Familiarity with Google Cloud Platform tools including BigQuery, Vertex AI, Dataflow, and Cloud Run, or Databricks and Spark.

Skills and Tools

Python and SQL
Machine learning libraries including scikit-learn, XGBoost, LightGBM, PyTorch, and TensorFlow
Data manipulation tools such as pandas and PySpark
Entity resolution, fuzzy matching, clustering, embeddings, and similarity-based techniques
Production machine learning workflows, versioning, monitoring, and CI/CD practices

Salary and Benefits

Flexible working environment designed to support a positive work-life balance
Responsible paid time off policy allowing team members to take necessary time to rest and recharge

About the Company

impact.com operates the world's leading commerce partnership marketing platform, transforming how businesses grow by enabling them to discover, manage, and scale partnerships across the entire customer journey. Over 5,000 global brands rely on the platform to power performance-based growth through trusted relationships.

How to Apply

Interested candidates should submit their application directly on the official company careers page.

Skills and tech stack

PythonPyTorchTensorFlowSQLGCPSparkNLPMLOps

Questions candidates ask

What is the primary focus of the Senior Data Scientist role at impact.com?

The primary focus is managing the analytical and technical foundation of product data quality, including catalog hygiene, transaction matching, classification modeling, deduplication, and global product identity.

Where is this job located?

This position is located in Cape Town.

What level of experience is required for this position?

Candidates must have 5+ years of experience in data science, ML engineering, or analytics engineering, with at least 2+ years focused on product data, catalog quality, entity resolution, search/retrieval, or e-commerce analytics.

What technical skills are needed?

Required technical skills include Python, SQL, ML libraries like scikit-learn, XGBoost, LightGBM, PyTorch, or TensorFlow, and data manipulation tools like pandas and PySpark.

What perks and benefits are offered?

The company offers flexible working arrangements supported by a responsible paid time off policy for rest and recharge.

Ready to apply?

The application is on the official impact.com careers page.

Apply on company site