AI/ML Data Engineer | Unstructured Data, PySpark, Python, Vector Search, RAG Architectures, Cloud (GCP/AWS) Apply Logo

Build and maintain scalable, robust data pipelines for unstructured content, ensuring high data quality and performance efficiency

Develop algorithms for document classification, cleansing, and enrichment to feed AI/ML systems

Integrate data workflows with LLM pipelines supporting RAG architectures for semantic search and Question-Answering (QA) systems

Engineer and optimize vector embeddings, document chunking, and metadata tagging for AI applications

Collaborate closely with AI architects, data scientists, and platform teams to design end-to-end AI solutions

Implement automation, monitoring, and security best practices to ensure system reliability and compliance

Support project lifecycle activities, including proof-of-concept, testing, deployment, and ongoing monitoring

Share domain expertise, conduct knowledge sharing, and mentor team members