Haystack
← Back to Jobs
Technology

AI Data Engineer

CLPS GlobalNew York, NY🇺🇸United StatesPosted 12 Aug 2026

Quick Overview

Work Type
On Site
Level
Mid Senior

Job Description

Job Description:
Role -  AI Data Engineer
Location - NYC,  NY- Hybrid (Local candidates only)
Employment Type: Fulltime
Experience: 9+ years
 
Mandatory Skills: Python, Data Engineering, ETL/ELT, Data Pipelines, LLM Applications, Agentic AI, RAG, LangChain, LangGraph, LlamaIndex, Vector Databases, Kubernetes, Cloud Platforms (AWS/Azure/Google Cloud Platform), Docker, CI/CD

Required Qualifications

  • Strong experience in  Python application development . 
  • Strong background in  data engineering, data analytics, BI, or data application development . 
  • Experience with cloud platforms and  Kubernetes-based application/pipeline deployment . 
  • Strong hands-on experience building  production-grade data pipelines . 
  • Strong understanding of data architecture, data processing, ETL/ELT, and data integration.
  • Experience working with databases, data warehouses, and/or modern data platforms.
  • Experience building  data-facing applications or applications that interact directly with data and analytics platforms. 
  • Hands-on experience developing  LLM-powered applications . 
  • Understanding of  AI agent/harness engineering patterns and LLM application architecture. 
  • Experience working with APIs, databases, data platforms, and enterprise data sources.  
  • Cloud development experience with  Kubernetes-based deployment . 
  • Strong software engineering fundamentals including Git, testing, CI/CD, and production deployment.
  • Demonstrated ability to work independently and take ownership from requirements through delivery.
  • Strong analytical, troubleshooting, and communication skills.


Preferred Qualifications

  • Experience with agentic AI, LLM orchestration, RAG, or tool-using agents.
  • Experience with frameworks such as  LangChain, LangGraph, LlamaIndex , or similar technologies. 
  • Experience with vector databases and retrieval pipelines.
  • Experience integrating LLMs with enterprise data platforms.
  • Experience building dashboards, analytics applications, self-service data applications, or other data-centric user experiences.
  • Experience with AWS, Azure, or Google Cloud Platform.
  • Experience with Docker and Kubernetes.

Skills

Docker
AWS
ETL
Azure
Git
Google Cloud
Kubernetes
LLM
Python

Similar jobs