Senior Generative AI Engineer – Enterprise LLMs

Ethereum Technologies; Salt Lake City (UT); On-site; USD 97,000 - 138,000; Full time

Job summary

Ethereum Technologies in Salt Lake City, UT seeks a Generative AI Engineer to develop AI-powered applications using LLMs, RAG, and agentic AI. You will design conversational interfaces, integrate foundation models, and build enterprise AI solutions with Python, modern AI frameworks, and cloud services.

The role emphasizes prompt engineering, vector databases, and deployment of AI workflows at scale, including server-side APIs, back-end services, and AI security practices.

Qualifications

• 4–8 years of software/AI engineering experience with hands-on GenAI.
• Strong Python programming and RESTful API experience.
• Hands-on experience with LangChain, LangGraph, or LlamaIndex.
• Experience with vector databases and semantic search.

Responsibilities

• Design, develop, and deploy Generative AI apps using OpenAI, Azure OpenAI, Anthropic, and other LLM platforms.
• Build chatbots, virtual assistants, and enterprise copilots.
• Develop prompt engineering strategies (zero-shot, few-shot, chain-of-thought).
• Integrate LLM capabilities into enterprise apps via APIs and backend services.
• Create RAG pipelines and document ingestion and embedding workflows.
• Work with vector databases and semantic search tools (Pinecone, ChromaDB, FAISS, Weaviate).
• Develop AI agents and multi-agent workflows using LangChain, LangGraph, and LlamaIndex.

Skills

Python

RESTful APIs

LLMs

RAG

Prompt engineering

Vector databases

Cloud AI services

Tools

LangChain

LangGraph

LlamaIndex

Pinecone

ChromaDB

FAISS

Weaviate

FastAPI

Docker

Kubernetes

Job description

Ethereum Technologies in Salt Lake City, UT seeks a Generative AI Engineer to develop AI-powered applications using LLMs, RAG, and agentic AI. You will design conversational interfaces, integrate foundation models, and build enterprise AI solutions with Python, modern AI frameworks, and cloud services.

The role emphasizes prompt engineering, vector databases, and deployment of AI workflows at scale, including server-side APIs, back-end services, and AI security practices.