Senior Python AI Backend Engineer - RAG & Memory

RiVi Consulting Group L.L.C; Green Bay (WI); On-site; USD 90,000 - 140,000; Full time

Job summary

RiVi Consulting Group L.L.C is seeking an engineer to scale backend infrastructure and deepen agentic capabilities. This role will build memory layers, RAG pipelines, and ontological structures that enable our AI to serve as a true co-pilot for logistics professionals.

The position requires production-grade asynchronous Python (FastAPI/Pydantic) and hands-on work with LangGraph/LangChain, focusing on performance, state management, and secure SDLC practices in a GCP environment.

Qualifications

• Expert Python engineering: production-grade, asynchronous Python (FastAPI/Pydantic) with a focus on performance and scalability.
• Agentic frameworks & reasoning: hands-on experience with LangGraph, DSPy, or LangChain. Understand state management, agent loops, and reliable tool-calling; evaluations a bonus.
• Knowledge graphs & ontologies: experience building or working with ontologies.
• Advanced memory management: long-term memory using vector databases and schemas to maintain context over long horizons.
• RAG & LLMs: experience with RAG optimization (reranking, query transformation) and/or fine-tuning LLMs for domain-specific reasoning.
• Experience with GCP is preferred- understands Secure SDLC practices.

Responsibilities

• Quick learner with high agency.
• A product engineer mindset.
• Comfort with ambiguity and a sense of extreme ownership.
• Experience working in a fast paced environment.

Skills

Python engineering

LangGraph/LangChain

Knowledge graphs

Memory management

RAG/LLMs

GCP knowledge

Tools

FastAPI

Pydantic

LangGraph

LangChain

DSPy

Job description

RiVi Consulting Group L.L.C is seeking an engineer to scale backend infrastructure and deepen agentic capabilities. This role will build memory layers, RAG pipelines, and ontological structures that enable our AI to serve as a true co-pilot for logistics professionals.

The position requires production-grade asynchronous Python (FastAPI/Pydantic) and hands-on work with LangGraph/LangChain, focusing on performance, state management, and secure SDLC practices in a GCP environment.