Job Description & Details
This is a heavy-hitting enterprise role focused on moving AI prototypes into actual production systems rather than just writing experimental Jupyter notebooks. If you enjoy bridging the gap between cutting-edge LLMs and robust full-stack applications, this 12-month contract will keep you deeply challenged.
What You'll Actually Be Doing
You will spend your days building out end-to-end AI capabilities for enterprise software, which means designing RAG pipelines, managing vector stores, and setting up agentic workflows that actually behave reliably in production. Beyond the AI layer, you'll be writing clean backend services in Python and occasionally jumping into React to wire up the frontend interfaces so users can interact with these models seamlessly. Expect to spend a significant amount of time optimizing for latency, cost, and output accuracy while navigating enterprise-grade security and governance standards.
The Core Tech Stack
Your bread and butter here will be Python for backend services and AI orchestration, paired with React for frontend touchpoints. You absolutely must know your way around Large Language Models, prompt engineering, and building production-grade RAG architectures with strict evaluation frameworks. Because this is enterprise-scale engineering, you'll also need solid experience integrating RESTful APIs, working with cloud platforms like AWS, Azure, or GCP, and handling MLOps tasks like CI/CD pipelines and model monitoring.
Interview Expectations
Expect the hiring team to grill you on how you handle failure modes in RAG systems, such as dealing with hallucination drift or optimizing retrieval latency under heavy enterprise loads. They want to see that you understand the pragmatic trade-offs between cost and model performance, so be prepared to talk through a time you scaled an AI application in production and how you monitored its health.
Application Advice
Make sure your resume doesn't just list AI buzzwords, but explicitly highlights production deployments where you built RAG pipelines or scaled Python APIs. Drop exact keywords like Retrieval-Augmented Generation, agentic workflows, Python, React, and MLOps right into your experience bullets to clear the automated ATS filters and catch the eye of the engineering manager.