Data Engineer

Responsibilities

• Design and build backend services using Python and FastAPI
• Develop, test, and deploy GenAI applications in a production setting
• Build and maintain LLM pipelines (e.g., OpenAI, HuggingFace Transformers, LangChain)
• Construct scalable data pipelines for ingesting and structuring archival content
• Interface with graph databases (e.g., Neo4j, Memgraph) for relationship mapping
• Collaborate with AI/ML engineers, designers, and other stakeholders to integrate LLM outputs with UI and user workflows
• Implement CI/CD pipelines and manage on-premise or VM-based deployment

Requirements

• Good understanding of a global import export environment & the documentation requirement for the same
• Familiarity in working across ERP systems and system integrations.
• Strong proficiency in Python, with experience in FastAPI
• Experience developing and deploying LLM-based applications (Azure OpenAI API, HuggingFace, etc.)
• Background in data engineering-working with large-scale unstructured text, ETL workflows
• Familiarity with graph databases and knowledge representation
• Exposure to CI/CD pipelines and deploying services in on-premise or virtual machine environments
• Track record of taking GenAI applications from development to real-world usage