Senior Python AI Engineer, GenAI & RAG Apps

Machine Learning Technologies, LLC; Wilmington (DE); On-site; USD 120,000 - 180,000; Full time

Job summary

Machine Learning Technologies, LLC is seeking a seasoned Python AI Developer in the United States to build AI-driven applications and data pipelines. You will design backend microservices in Python and drive production-ready implementations across cloud platforms.

You will implement Retrieval-Augmented Generation (RAG) and orchestrate AI agents with LangChain, LangGraph, or CrewAI, integrating LLMs with vector stores and external REST APIs, while optimizing performance and deployment with Docker

Qualifications

• 7+ years of total software experience with deep proficiency in Python.
• Hands-on experience with GenAI, NLP, prompt engineering, and vector stores.
• Knowledge of web frameworks such as FastAPI, Flask, or Django.
• Familiarity with MLOps practices, Git version control, and containerization.

Responsibilities

• Design and build AI-driven applications, data pipelines, and microservices using Python.
• Implement Retrieval-Augmented Generation (RAG) and orchestrate AI agents using tools like LangChain, LangGraph, or CrewAI.
• Integrate Large Language Models (LLMs) with enterprise vector databases and external REST APIs.
• Optimize backend performance and deploy production-ready code via Docker and cloud platforms (AWS, Azure, GCP).

Skills

Python programming

GenAI

NLP

Prompt engineering

Vector databases

MLOps practices

Git version control

Containerization

Tools

LangChain

LangGraph

CrewAI

FastAPI

Flask

Django

Docker

AWS

Azure

GCP

REST APIs

Job description

Machine Learning Technologies, LLC is seeking a seasoned Python AI Developer in the United States to build AI-driven applications and data pipelines. You will design backend microservices in Python and drive production-ready implementations across cloud platforms.

You will implement Retrieval-Augmented Generation (RAG) and orchestrate AI agents with LangChain, LangGraph, or CrewAI, integrating LLMs with vector stores and external REST APIs, while optimizing performance and deployment with Docker