AI Data Knowledge Engineer

About the job

Requirements: • 8 - 12 + years of data or ML engineering experience, with 3 + years in semantic search, RAG, or vector database architecture. • Proficiency with Python, SQL, and frameworks such as LangChain, LlamaIndex, or Haystack. • Hands-on experience with vector databases (Pinecone, Weaviate, Qdrant, Chroma) and cloud data stores (AWS S3 DynamoDB, Redshift). • Deep understanding of embedding models (OpenAI, Cohere, Sentence Transformers) and performance tuning for large-scale retrieval. • Strong data pipeline experience (Airflow, Kafka, Temporal) and understanding of MLOps fundamentals. • Familiarity with industrial data (SAP, Maximo, OSI PI, SCADA, MES) preferred. • Excellent communication and documentation skills, able to translate data architecture into business and engineering language.

Requirements

• Python
• SQL
• LangChain
• LlamaIndex
• Haystack
• Pinecone
• Weaviate
• Qdrant
• Chroma
• AWS S3
• DynamoDB
• Redshift

Preferred Technologies

• Python
• SQL
• LangChain
• LlamaIndex
• Haystack
• Pinecone
• Weaviate
• Qdrant
• Chroma
• AWS S3
• DynamoDB
• Redshift

About the company

null