Description
We are building an AI-powered SaaS platform and are looking for a senior AI/ML Engineer to architect and develop the AI layer from the ground up. This is a long-term hourly opportunity starting with a defined Phase 1 scope, with additional platform development planned for future phases. Platform Vision: • Multi-tenant SaaS architecture with AI capabilities built into the platform • LLM-powered core functionality with Retrieval-Augmented Generation (RAG) pipelines • AI agents for multi-step workflows and intelligent user interactions • Scalable cloud infrastructure on AWS or GCP with containerized deployments • Subscription billing, user authentication, and client-level analytics dashboard Phase 1 Scope: • Design and implement a RAG pipeline, including data ingestion, chunking, embeddings, and vector retrieval • Integrate modern LLMs such as GPT-4o or Claude with effective prompt engineering and conversation memory • Build an AI agent layer using LangChain or LangGraph for workflow automation • Develop a clean, scalable multi-tenant backend using FastAPI • Deploy the platform using Docker and Kubernetes on AWS or GCP • Create a basic analytics dashboard for platform usage, performance, and client-level insights Required Skills: • Proven experience building and deploying production AI applications or AI-powered SaaS platforms • Strong Python development skills • Experience with LangChain, LangGraph, RAG pipelines, and LLM integration • Experience designing scalable multi-tenant