AI Engineer Intern (Agent Infrastructure)

Who We Are Quest is building the human execution layer for AI agents, where AI agents and businesses can hire real people to get things done in the physical world. AI can reason, plan, and coordinate, but it can't run an errand, fix a leaky tap, or deliver a package. Quest is the missing infrastructure that connects the agentic AI economy to real-world execution, starting in Southeast Asia. We're on a mission to unlock local economic opportunities by making it radically easy for humans and AI agents alike to hire real people, safely and efficiently. Backed by top-tier investors including Goodwater Capital, Antler, and leading tech angels, Quest is scaling rapidly to become the default way agents "hire a human." Job Summary We're looking for an AI Engineer Intern to help build Quest's MCP (Model Context Protocol) server and agent-facing tooling to enable AI agents to discover, hire, and coordinate with real humans through Quest. You'll also get exposure to our production ML systems as a secondary track alongside the core agent infra work. What You'll Do Agent Infrastructure (primary focus) Build and ship MCP server tools Design delegation objects so agents can safely act on a user's behalf Prototype and test end-to-end agent workflows (e.g., an agent posting a quest, matching to a Hero, releasing payment) Contribute to technical specs, experimentation logs, and Quest's developer experience Matching & Moderation Microservices (secondary) Support improvements to our production matching system Contribute to our UGC moderation pipeline, including trust-tier review and LLM-assisted report handling You Might Be a Great Fit If You Have hands-on experience building and shipping Python backend services (Flask/FastAPI) Understand, or are eager to quickly learn, the Model Context Protocol (MCP) and agent tool-calling patterns Are comfortable with LLM APIs (Gemini, Anthropic/Claude API) and have some exposure to NLP/embeddings (sentence-transformers, PGVector, VertexAI Embeddings) Think carefully about safety and authorization design, not just feature velocity Are curious, resourceful, and self-driven Have startup experience or exposure (a big plus) Can commit for at least 3 months Our Internship Period Options 6 months full-time from Aug '26 onwards (Preferred option) 3 months part-time from Aug '26 onwards + 2 month full-time from Nov/Dec '26 onwards 3 months part-time from Aug '26 onwards