Senior Generative AI Engineer - Enterprise LLMs & RAG

Realign Llc; Newark (DE); On-site; USD 130,000 - 190,000; Full time

Job summary

Realign Llc in Newark, Delaware is seeking an experienced Generative AI Engineer to design, develop, and deploy AI solutions for production use. You will work with LLMs, RAG, vector databases, and cloud platforms to deliver enterprise-grade GenAI applications.

Responsibilities include building production-ready AI apps, implementing prompt engineering and evaluation frameworks, and collaborating with data scientists, engineers, and business stakeholders to ensure scalable, responsible AI

Qualifications

• Hands-on experience with generative AI in production environments.
• Experience with large language models (LLMs) and retrieval-augmented generation (RAG).
• Familiarity with vector databases and cloud AI platforms.

Responsibilities

• Design, develop, and deploy Generative AI solutions for enterprise business use cases.
• Build and maintain production-ready applications utilizing LLMs such as GPT, Claude, Gemini, Llama, or similar models.
• Develop RAG-based solutions using vector databases such as Pinecone, FAISS, ChromaDB, or Azure AI Search.
• Implement prompt engineering, prompt tuning, and model evaluation frameworks.
• Collaborate with business stakeholders, architects, data scientists, and engineering teams to deliver scalable AI solutions.
• Monitor production AI applications for performance, accuracy, latency, and cost optimization.
• Design AI agents and workflow automation using frameworks such as LangChain, LangGraph, LlamaIndex, AutoGen, or Semantic Kernel.
• Implement responsible AI controls, security, governance, and compliance requirements.
• Troubleshoot and resolve production issues related to AI systems.

Skills

Artificial intelligence

LLM

RAG

LangChain

LlamaIndex

AutoGen

Semantic Kernel

Tools

Pinecone

FAISS

ChromaDB

Azure AI Search

Job description

Realign Llc in Newark, Delaware is seeking an experienced Generative AI Engineer to design, develop, and deploy AI solutions for production use. You will work with LLMs, RAG, vector databases, and cloud platforms to deliver enterprise-grade GenAI applications.

Responsibilities include building production-ready AI apps, implementing prompt engineering and evaluation frameworks, and collaborating with data scientists, engineers, and business stakeholders to ensure scalable, responsible AI