Python Data Engineer

Quick Facts

• Role: Python Data Engineer
• Work mode: Hybrid
• Experience: 8+ years

Description

Build and deploy data engineering pipelines using Python and big-data technologies, with hands-on GenAI/LLM integration. Work across the stack including data transformations, API/back-end services, and CI/CD-driven releases. Apply RAG and vector/semantic search concepts to enable retrieval-aware AI behavior.

Responsibilities

• Design and develop data engineering pipelines and transformations
• Analyze data lineage/data flows using static analysis (AST-based and pattern-based)
• Build LLM-enabled capabilities (prompt design, tool/function calling, agent orchestration)
• Implement retrieval-augmented generation using vector/semantic search concepts
• Design APIs and backend services; support front-end fundamentals for usable interfaces
• Create build/test automation and deliver releases across environments via CI/CD

Requirements

• 8+ years of Python experience
• Strong OOP and functional design skills in Python
• Strong software engineering fundamentals (data structures, algorithms, complexity analysis)
• Experience with data lineage/data flow analysis using AST/pattern-based static analysis; ability to read multiple languages
• Hands-on GenAI/LLM experience (prompt design, tool/function calling, agent orchestration)
• Understanding of RAG and vector/semantic search
• Experience designing APIs and backend services; basic front-end fundamentals
• Pipeline and deployment experience (build/test automation, CI/CD, releases across environments)
• Data manipulation and transformation expertise

Benefits

• Full-time position