Note: The job is a remote job and is open to candidates in USA. Dice is a global leader in delivering innovative IT solutions and services. They are hiring RAG-first GenAI engineers to build LLM-powered applications and agentic workflows for enterprise clients.

Responsibilities

• Architect end-to-end RAG: chunking, embedding selection, hybrid/semantic search, re-ranking, citation and evaluation
• Build LLM-powered microservices and APIs (FastAPI / REST)
• Integrate and orchestrate LLMs (OpenAI, Claude, Gemini, Llama) into product and internal workflows
• Add agentic behavior on top of RAG: tool-calling, multi-step task execution, guardrails, hallucination handling
• Stand up and tune vector-store infrastructure; deploy and monitor in production

Skills

• Strong Python
• End-to-end RAG experience
• Vector databases (Pinecone, Weaviate, pgvector, FAISS, or similar)
• LLM API integration (OpenAI / Anthropic / Gemini / Llama)
• LangChain and/or LlamaIndex
• FastAPI / REST and one cloud (AWS, Azure, or Google Cloud Platform)
• LangGraph, MCP, DSPy
• Knowledge graphs / Neo4j, evals/LangSmith, MLOps

Company Overview

Company H1B Sponsorship