LLM Integration Engineer: RAG Pipelines & LangChain

Zoho; United States; Remote; USD 120,000 - 180,000; Full time

Job summary

Fyerx in the United States seeks an experienced LLM Integration / LangChain Engineer to design, develop, and implement orchestration layers connecting enterprise data assets with cutting-edge generative AI models.

You will build production-grade Retrieval-Augmented Generation (RAG) pipelines, program multi-agent reasoning loops using LangChain, LangGraph, or LlamaIndex, and establish secure system middleware to safely deploy AI capabilities at scale.

Qualifications

• 4 to 8 years of enterprise backend/web engineering or data pipelines experience.
• 2+ dedicated years writing production-level code around LLM infrastructures.
• Strong mastery of Python or TypeScript, vector representations, and prompt engineering.

Responsibilities

• Design and construct advanced LLM applications and orchestrations using LangChain, LangGraph, LlamaIndex or AutoGen.
• Build production-grade RAG architectures with dynamic context chunking and reranking.
• Develop multi-agent reasoning chains, tool calls, memory caching, and guardrail validations.
• Expose and consume high-throughput API endpoints linking OpenAI/Anthropic/HuggingFace models with internal data sources.

Skills

Python/TypeScript

LLM fundamentals

Async Web Apps

SQL

Education

ML/Cloud cert (AWS/GCP/Azure)

Tools

LangChain

LangGraph

LlamaIndex

AutoGen

GPTCache

Job description

Fyerx in the United States seeks an experienced LLM Integration / LangChain Engineer to design, develop, and implement orchestration layers connecting enterprise data assets with cutting-edge generative AI models.

You will build production-grade Retrieval-Augmented Generation (RAG) pipelines, program multi-agent reasoning loops using LangChain, LangGraph, or LlamaIndex, and establish secure system middleware to safely deploy AI capabilities at scale.