Senior AI Engineer for AI Persona System

Role Overview

We are looking for a seasoned Senior AI Engineer to help lead the development of a cutting-edge, real-time AI persona system that integrates large language models (LLM), memory, and retrieval mechanisms specifically designed for educational purposes. You will be instrumental in shaping and scaling this innovative solution, focusing on creating a highly personalized and latency-optimized interaction experience. This role could evolve into a leadership position as the product scales—especially for those who thrive in fast-moving, high-ownership environments.

Responsibilities

• Architect and implement a modular persona system (LLM + memory + retrieval) designed for real-time interaction.
• Optimize system for low-latency, multi-user performance at scale.
• Lead personalization logic using memory, user modeling, and contextual adaptation.
• Build with modularity and extensibility in mind across future use cases.
• Collaborate closely with stakeholders to align AI capabilities with product goals and roadmap.

Required Skills

• Hands-on experience with LLM orchestration and production AI systems.
• Proven track record scaling real-time, high-concurrency systems.
• Expertise in retrieval-augmented generation (RAG) and vector search.
• Strong grasp of latency, cost, and infrastructure optimization.

Nice to Have

• Background in education technology or adaptive learning systems.
• Familiarity with persona tuning techniques (e.g., prompt engineering, memory design).
• Experience with LangChain, FAISS, or similar frameworks.
• Interest in building AI systems with real-world impact and multi-domain extensibility.