Senior Data Scientist (Product Data)

Location: Cape Town, South Africa

Company

hirify.global operates a commerce partnership marketing platform that helps brands manage affiliate, creator, and customer referral partnerships.

What you will do

• Develop, deploy, and maintain ML models for product classification, taxonomy assignment, ranking, search, and retrieval.
• Analyze catalog and sales transaction data quality, including completeness, consistency, match rates, GPID coverage, freshness, and duplicate rates.
• Build matching, deduplication, entity resolution, and product variant pipelines across retailers, brands, catalogs, and transactions.
• Research vector search, semantic similarity, embeddings, vector databases, and product graph infrastructure for search and recommendations.
• Create dashboards, KPIs, alerts, and anomaly detection systems to monitor data quality and model performance.
• Take research prototypes into production by owning deployment, testing, monitoring, CI/CD, observability, reliability, and iteration.

Requirements

• 5+ years of experience in data science, ML engineering, or analytics engineering, including 2+ years focused on product data, catalog quality, entity resolution, search/retrieval, or e-commerce and marketplace analytics.
• Strong Python and SQL skills, with experience using ML libraries such as scikit-learn, XGBoost, LightGBM, PyTorch, or TensorFlow, plus pandas or PySpark.
• Experience building production-grade data pipelines and deploying ML models independently, including testing, version control, CI/CD, monitoring, evaluation, retraining, and A/B testing.
• Practical experience with classification, fuzzy matching, clustering, embeddings, similarity techniques, data profiling, anomaly detection, and large-scale exploratory analysis.
• Strong foundations in statistics and ML, with the ability to design experiments, validate models, interpret results, and communicate actionable recommendations.
• Bachelor’s degree in a quantitative field such as computer science, statistics, mathematics, or engineering; a Master’s or PhD is preferred.

Nice to have

• Experience with vector databases such as FAISS, Pinecone, Weaviate, Milvus, or pgvector, and search systems such as Elasticsearch or Solr.
• Experience with graph databases and analytics, including Neo4j, NetworkX, graph algorithms, and link prediction.
• Knowledge of NLP, multimodal modeling, recommendation systems, product identifiers such as GTIN, UPC, EAN, MPN, and SKU hierarchies.
• Familiarity with GCP, BigQuery, Vertex AI, Dataflow, Cloud Run, Looker, Databricks, Spark, master data management, or data governance.

Culture & Benefits

• Flexible working supported by a responsible PTO policy and a focus on work-life balance.
• Up to 12 fully covered therapy or coaching sessions per year, with additional dependent coverage.
• Monthly gym reimbursement, technology stipend for a home office, and monthly internet allowance.
• RSUs with a three-year vesting schedule, pending Board approval.
• Free Coursera access, PXA courses, and paid parental leave of 26 weeks for the primary caregiver and 13 weeks for the secondary caregiver.