Data Engineer – Applied ML
Core
Build LLM-powered and ML-based pipelines to classify, normalize, structure, and match product, brand, and category data at scale for a digital intelligence platform.
Role type
Senior Applied ML Data Engineer
Builds
Production pipelines for product taxonomy and entity resolution
Domain
E-commerce / Retail Intelligence / NLP
Deliverable
production ML models
Required skills
Python, LLM application development, LangGraph, Spark/PySpark, Databricks, text classification, NLP methods, data quality evaluation, cloud infrastructure (AWS)
Preferred skills
Taxonomy/entity resolution experience, open-source model fine-tuning
Technologies
LangGraph, LangChain, Hugging Face, OpenAI, Anthropic, Spark, Databricks, AWS
Responsibilities
Design and build LLM/ML pipelines for data classification and normalization; Build agentic workflows to automate complex data tasks; Choose appropriate ML approaches balancing accuracy, cost, and latency; Scale solutions over billions of records; Build evaluation frameworks and monitoring; Take solutions from POC to production.
Seniority
Senior, hands-on IC
