GenAI Python Engineer: LLMs, RAG & LangChain

Pi-Square Technologies LLC; Minneapolis (MN); On-site; USD 120,000 - 180,000; Full time

Job summary

Pi-Square Technologies LLC is seeking an experienced Python Developer specializing in GenAI, LLMs, LangChain, LangGraph, and retrieval-augmented generation. You will design, develop, and deploy AI-powered applications with scalable cloud architectures.

Responsibilities include building GenAI solutions, integrating LLMs with diverse data sources, and optimizing prompt strategies and retrieval mechanisms. Collaboration across teams will ensure enterprise-grade, reliable AI deployments.

Qualifications

• Strong hands-on Python development experience.
• Expertise with LLMs (OpenAI, Azure OpenAI, Anthropic, etc.).
• Experience with LangChain and LangGraph.
• Knowledge of RAG architectures and retrieval strategies.
• Experience with vector databases such as Pinecone, ChromaDB, FAISS, Weaviate.
• Familiarity with prompt engineering and AI agents.
• Experience with REST APIs and microservices.
• Cloud platform familiarity (Azure, AWS, GCP).
• Strong debugging, testing, and optimization skills.

Responsibilities

• Build and deploy GenAI and Agentic AI solutions.
• Develop RAG-based applications for enterprise use cases.
• Integrate LLMs with structured and unstructured data sources.
• Design workflows using LangChain and LangGraph.
• Optimize model performance, prompt strategies, and retrieval mechanisms.
• Collaborate with cross-functional teams to deliver scalable AI solutions.

Skills

Python development

LLMs

LangChain

LangGraph

RAG

Prompt engineering

AI agents

REST APIs

Cloud platforms

Tools

Pinecone

ChromaDB

FAISS

Weaviate

Job description

Pi-Square Technologies LLC is seeking an experienced Python Developer specializing in GenAI, LLMs, LangChain, LangGraph, and retrieval-augmented generation. You will design, develop, and deploy AI-powered applications with scalable cloud architectures.

Responsibilities include building GenAI solutions, integrating LLMs with diverse data sources, and optimizing prompt strategies and retrieval mechanisms. Collaboration across teams will ensure enterprise-grade, reliable AI deployments.