AI Developer
On-siteSunnyvale, California, United States
Job Summary
Design and develop production-ready AI agents for enterprise use cases using modern LLM frameworks and Node.js. Implement Retrieval-Augmented Generation (RAG) pipelines to improve model accuracy while integrating LLMs with enterprise data sources, APIs, and business workflows. Optimize prompt engineering, tool calling, memory, and agent orchestration to enhance application performance. Collaborate with cross-functional engineering and product teams to deliver scalable AI-driven solutions. Troubleshoot and refine backend services to ensure robust execution. This role focuses on building next-generation intelligent applications and autonomous AI agents within a team leveraging Large Language Models and modern Node.js development.
Required Qualifications
- Strong hands-on experience with Node.js
- Proven experience building AI Agents (must-have)
- Strong experience working with Large Language Models (LLMs)
- Experience designing and implementing RAG (Retrieval-Augmented Generation) solutions
- Experience integrating LLMs with APIs, databases, and external tools
- Solid understanding of prompt engineering and AI application architecture
- Ability to build scalable backend services for AI applications
- Node.js
- AI Agents (Hands-on Development)
- Large Language Models (LLM)
- Retrieval-Augmented Generation (RAG)
Desired Qualifications
- Experience with LangChain, LangGraph, LlamaIndex, CrewAI, AutoGen, Semantic Kernel, or similar agent frameworks
- Experience with vector databases such as Pinecone, Weaviate, Milvus, or ChromaDB
- Experience with OpenAI, Anthropic, Gemini, or other foundation models
- Cloud experience with Azure, AWS, or GCP
- Docker/Kubernetes experience
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.