AI Backend Engineer - Part-time - Worldwide

🤖 AI/Backend Engineer

(Focus: LLMs, RAG Pipelines, Generative AI + Backend Development)

We’re hiring an AI/Backend Engineer to build the infrastructure behind an intelligent, event-driven digital asset. This role blends backend engineering with LLM orchestration, generative AI systems, and real-time data processing. You’ll be responsible for the server-side logic, pipeline integration, and AI-driven features of the platform.

🧠 Responsibilities

• Design and implement backend services using Python (Flask, FastAPI, etc.).
• Architect and manage RAG pipelines, memory models, and LLM orchestration.
• Build endpoints and data flows to power the frontend experience.
• Prototype and deploy event-driven AI features based on user interaction.
• Optimize backend performance, scalability, and latency for AI workloads.

✅ Required Skills

• Strong Python backend development experience (e.g., Flask, FastAPI).
• Solid knowledge of LLMs, LangChain, OpenAI, RAG pipelines.
• Understanding of data modeling and scalable architecture for real-time systems.
• Comfortable deploying to cloud environments (GCP, AWS).
• Familiarity with CI/CD, version control, and backend testing.

💡 Nice to Have

• Experience with vector databases, memory frameworks, and async workflows.
• Understanding of ANSI or structured data standards is a bonus.
• Interest in human-in-the-loop AI systems or intent modeling.