AI Backend Engineer

RiVi Consulting Group L.L.C; Green Bay (WI); On-site; USD 120,000 - 180,000; Full time

Job summary

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

The role requires expert Python engineering, hands-on experience with LangGraph, DSPy, or LangChain, and knowledge graphs/or ontologies, plus memory management using vector databases and schemas to

Qualifications

• Expert-level Python engineering for production-grade systems.
• Experience with memory layers, vector DBs, and long-term context.
• Familiarity with LangGraph, DSPy, LangChain and tool-calling.
• GCP experience is preferred.

Responsibilities

• Scale backend infrastructure and deepen agentic capabilities.
• Build memory layers, RAG pipelines, and ontologies for AI co-pilot.

Skills

Python engineering

Async Python

Agentic frameworks

LangGraph

Knowledge graphs

RAG optimization

GCP

Memory management

Tools

LangChain

DSPy

LangGraph

Pydantic

FastAPI

Vector databases

Job description

We are looking for an engineer to help scale our backend infrastructure and deepen our agentic capabilities. This individual will not just be wrapping APIs; they will be building the memory layers, RAG pipelines, and ontological structures that allow our AI to serve as a true co-pilot for logistics professionals.

Technical Requirement

• - Expert Python Engineering: Production-grade, asynchronous Python (FastAPI/Pydantic) with a focus on performance and scalabilit
• y.- Agentic Frameworks & Reasoning: Hands-on experience with LangGraph, DSPy, or LangChain. Must understand state management, agent loops, and reliable tool-calling. Experience with evaluations is a significant bonu
• s.- Knowledge Graphs & Ontologies: Experience building or working with ontologie
• s.- Advanced Memory Management: Implementation of "long-term memory" using vector databases and schemas to maintain context over long horizon
• s.- RAG & LLMs: Experience with RAG optimization (reranking, query transformation) and/or fine-tuning LLMs for domain-specific reasonin
• g.- Experience with GCP is preferr

Core Competenc

• - Quick learner with high age
• set.- Comfort with ambiguity and a sense of extreme owners
• hip.- Experience working in a fast paced environm