Senior Data Engineer

Youll design and implement core data pipelines and semantic data models that power AI solutions at a massive scale. Youll be instrumental in building the data infrastructure that enables high-quality retrieval, grounding, and reduced hallucination for multi-domain LLM applications. Youll work alongside global tech leaders to create meaningful impact across language, public sector, enterprise technology, and deep learning domains.

Responsibilities

• Design and build scalable data pipelines for multi-domain LLM applications.
• Implement semantic data models that enable high-quality information retrieval.
• Develop and optimize vector database solutions for embedding storage and retrieval.
• Create robust ETL/ELT systems for processing large-scale datasets.
• Build metadata enrichment pipelines to improve retrieval accuracy.
• Design GraphQL schemas for efficient data access patterns.
• Optimize chunking strategies and embedding pipelines for reduced hallucination.
  
  

• 5-10 years of hands-on experience in data engineering or data science.
• Expert-level proficiency in Python and SQL for data processing.
• Experience building data systems supporting 100+ million users or equivalent scale.
• Proven experience building and maintaining ETL/ELT systems at scale.
• Hands-on experience with GraphQL schema design and implementation.
• Working experience with vector databases (Pinecone, Milvus, or Weaviate).
• Experience with workflow orchestration tools (Airflow, Spark, or Flink).
  
  

• Experience in the hyperscaler domain (cloud platforms, distributed systems at scale).
• Experience with LLM applications and retrieval-augmented generation (RAG).
• Background in machine learning or NLP projects.
• Knowledge of semantic search and information retrieval systems.
• Experience with multi-tenant, globally distributed data architectures.