Lead Generative AI Engineer - LLMs, RAG, Vertex AI

Ethereum Technologies; Minneapolis (MN); On-site; USD 85,000 - 121,000; Full time

Job summary

Ethereum Technologies in Minneapolis seeks an experienced Lead Software Engineer specializing in Generative AI, ML, GCP, and Document AI. You will build enterprise GenAI apps, implement RAG architectures, fine-tune LLMs, and develop Agentic AI solutions.

You will design backend services with Python, FastAPI, and Docker, deploy AI applications on cloud platforms, and collaborate across teams to deliver scalable AI capabilities for enterprise clients.

Qualifications

• Experience building enterprise GenAI applications and agentic AI.
• Hands-on with RAG architectures, LLM fine-tuning, and prompt engineering.
• Proficiency in Python and API development (FastAPI/REST).
• Strong knowledge of document processing and information extraction.

Responsibilities

• Design and implement enterprise-grade Generative AI and Agentic AI solutions.
• Develop and deploy LLM-based applications using Vertex AI and other platforms.
• Build and optimize RAG pipelines with embeddings and vector databases.
• Implement LLM fine-tuning and prompt engineering techniques.
• Develop document processing solutions using Google Document AI, OCR, and structured data generation.
• Build AI agents using LangGraph, Google ADK, and CrewAI.
• Work with OpenAI APIs, open-source LLMs, and various LLM platforms.
• Apply ML techniques including supervised/unsupervised learning, RL, and NLP.
• Develop backend services and APIs using Python, FastAPI, Flask, and REST.
• Deploy and manage AI apps on Docker and cloud platforms (GCP/AWS/Azure).

Skills

Python programming

Generative AI

LLMs

RAG architectures

NLP

OpenAI APIs

Tools

Vertex AI

Google Document AI

LangGraph

Google ADK

CrewAI

PyTorch

Streamlit

Flask

FastAPI

Docker

Job description

Ethereum Technologies in Minneapolis seeks an experienced Lead Software Engineer specializing in Generative AI, ML, GCP, and Document AI. You will build enterprise GenAI apps, implement RAG architectures, fine-tune LLMs, and develop Agentic AI solutions.

You will design backend services with Python, FastAPI, and Docker, deploy AI applications on cloud platforms, and collaborate across teams to deliver scalable AI capabilities for enterprise clients.