AI Engineer / Forward-Deployed AI Engineer — LLMs, RAG, MCP, Agents & AI Systems

About the Project We are a small and growing technology team developing AI-driven products, intelligent automation, and software systems powered by modern AI models. We are looking for a practical AI Engineer / Forward-Deployed AI Engineer who can take real technical or business requirements and turn them into functional AI-powered solutions. The work may span LLMs, RAG, MCP, AI agents, tool calling, APIs, backend development, automation, data integration, and AI application architecture. We are starting with a small paid technical project to evaluate technical fit and collaboration. Candidates who perform well may be invited to work with us on a larger project and potentially an ongoing contract. --- What You’ll Be Working With We are interested in engineers who have practical experience across some or most of the following: - Large Language Models (LLMs) - Retrieval-Augmented Generation (RAG) - Model Context Protocol (MCP) - AI Agents and Agentic Systems - Tool and Function Calling - AI Workflow Automation - Embeddings and Vector Search - Vector Databases - Knowledge Bases - Prompt Engineering - LLM API Integration - AI Application Development - REST APIs - Python - FastAPI - Backend Development - PostgreSQL / Supabase - Git and GitHub Experience working with OpenAI, Anthropic, Claude, LangChain, LlamaIndex, MCP servers, vector databases, or agent frameworks is a plus. You don't need to have worked with every technology above. We care more about your ability to understand the architecture and combine the right components to solve a problem effectively. --- What We Mean by Forward-Deployed AI Engineering This isn't a role where you'll simply be asked to create another basic chatbot or AI demo. We are looking for someone who can take an unclear problem and turn it into an engineered solution. You should be comfortable with tasks such as: - Understanding technical and business requirements - Identifying useful AI opportunities - Choosing an appropriate LLM and architecture - Designing RAG pipelines - Connecting models to external tools and services - Building MCP-based integrations - Creating agentic workflows - Developing backend APIs - Working with databases and external data - Integrating AI into existing applications - Testing and debugging AI workflows - Iterating quickly based on results - Explaining architectural and technical decisions The ideal engineer can move through the complete process: Problem → Architecture → Prototype → Working AI System --- Initial Paid Technical Project The first engagement will be a small paid technical assignment. The purpose is to evaluate your ability to build a practical AI solution rather than simply discuss AI concepts. Depending on the project requirements, the task could involve one or more of the following: - Connecting an LLM to an application - Implementing a lightweight RAG pipeline - Creating a small MCP integration - Connecting external APIs or tools - Working with a vector database - Building an AI agent or workflow - Implementing structured LLM outputs - Creating a small Python/FastAPI service The exact requirements will be shared with the selected candidate. This is not intended to be a large production build. We want to see how you approach the problem, make technical decisions, write maintainable code, integrate the required components, and deliver a working result. --- How We’ll Evaluate You The initial project will help us assess: - Practical LLM engineering skills - RAG implementation knowledge - MCP understanding and integration ability - Agent and workflow design - Backend/API development - System architecture - Code quality and maintainability - Problem-solving ability - Ability to work independently - Communication - Documentation - Speed of iteration - Ability to turn requirements into a functioning prototype We are looking for engineering ability, not just familiarity with AI buzzwords.