Agentic AI Data Engineer#26-01044

Pleasanon, CA

Onsite Job Description

Role Overview

Seeking a hands-on Agentic AI Data Engineer to design and build intelligent AI-driven applications leveraging modern LLM frameworks and AWS ecosystem capabilities. The role involves developing scalable agent-based solutions, integrating enterprise data, and supporting end-to-end AI solution delivery from PoC to production.

Key Responsibilities

• 
  Develop and implement agentic AI applications with orchestration workflows using frameworks such as LangChain, LangGraph, or similar
  
• 
  Build and optimize RAG (Retrieval-Augmented Generation) pipelines, including embeddings, chunking strategies, versioning, and vector database integration
  
• 
  Integrate AI agents with enterprise data sources, including APIs, databases, data warehouses, and data lakes, handling both structured and unstructured data
  
• 
  Work within the AWS ecosystem (S3, Glue, Athena, Redshift, Lambda, etc.) to enable scalable data pipelines and AI workloads
  
• 
  Support proof-of-concepts, pilots, and production deployments of AI solutions
  
• 
  Implement traceability, reasoning, and observability for AI agents to ensure reliability and transparency
  
• 
  Collaborate with cross-functional teams (data engineering, architecture, business stakeholders) to align solutions with business use cases
  
• 
  Participate in technical discussions and contribute to solution design for evolving AI use cases
  Required Skills & Experience
  
• 
  2-5 years of hands-on experience in AI/ML and data engineering, with exposure to agentic AI development
  
• 
  Strong proficiency in Python and SQL
  
• 
  Experience building AI agent workflows and RAG-based solutions
  
• 
  Familiarity with vector databases and embedding techniques
  
• 
  Experience working with LLMs (OpenAI, Claude, or similar) in cloud and/or on-prem environments
  
• 
  Understanding of AWS services, especially related to data and AI (Bedrock is a plus)