Full-Stack AI Engineer

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Full-Stack AI Engineer based in India.

This role offers the opportunity to shape the intelligence behind an AI-powered teaching companion designed to support early-learning educators. You’ll own key artificial intelligence capabilities, including retrieval, generation, orchestration, and the logic that makes AI responses useful and dependable. Working across the full stack, you’ll connect intelligent capabilities with engaging product experiences while collaborating closely with backend, frontend, infrastructure, and product teams. You’ll have significant ownership over the architecture, quality, and evolution of the AI experience from launch through scale. The role combines deep technical challenges with strong product thinking, requiring a genuine curiosity about how educators use technology. You’ll also help advance personalization, multilingual capabilities, classroom insights, and other future-facing AI features. This is an opportunity to build highly visible technology with meaningful impact across education and learning.

Accountabilities

• Own the artificial intelligence capabilities powering the product, including retrieval, generation, models, orchestration, and supporting logic.
• Design and improve retrieval experiences that help educators quickly discover relevant videos, printables, activities, guides, and other learning resources.
• Build and refine content and data pipelines that ingest, structure, enrich, and organize multilingual educational content for accurate retrieval.
• Develop and integrate AI capabilities across the full technology stack, working closely with backend and frontend engineering teams.
• Design AI behavior, personality, system prompts, personas, tool usage, and guardrails with the end-user experience in mind.
• Drive the AI product from launch through continued evolution, identifying opportunities to improve functionality, personalization, and scalability.
• Continuously improve the quality, speed, reliability, and usefulness of AI-generated responses and recommendations.
• Use modern AI-assisted development tools to design, build, test, and iterate efficiently.
• Collaborate with infrastructure engineering to ensure AI services operate reliably, securely, and efficiently in the cloud.
• Establish evaluation frameworks, testing processes, monitoring, and quality controls for AI systems and maintain clear technical documentation.
• Partner closely with engineering and product teams, communicating technical thinking, progress, risks, and opportunities clearly.
• Contribute to the product roadmap, including initiatives such as deeper personalization, multilingual support, and classroom insights.
• Build AI experiences with privacy, security, and child-safety considerations in mind, including alignment with the Family Educational Rights and Privacy Act (FERPA) and Children's Online Privacy Protection Act (COPPA).

Requirements

• 5+ years of software engineering experience, with strong full-stack capabilities and the ability to work comfortably across backend and frontend systems.
• Proven hands-on experience building and shipping at least one production Large Language Model (LLM) or AI-powered application.
• Strong practical experience developing Retrieval-Augmented Generation (RAG) systems, including embeddings, vector databases, semantic search, and re-ranking.
• Strong understanding of retrieval quality, relevance, latency, reliability, and the factors that make AI-powered search dependable in production.
• Experience using modern AI-assisted development tools and incorporating AI effectively throughout the software development workflow.
• Strong Python skills and solid backend engineering fundamentals, including Application Programming Interfaces (APIs), databases, and data pipelines.
• Practical experience with LLM orchestration and prompt engineering using LangChain or comparable frameworks, including agent and tool design, system prompts, personas, and guardrails.
• Strong Amazon Web Services (AWS) experience across compute, storage, databases, containers, and monitoring.
• Familiarity with managed AI model services such as Amazon Bedrock and/or self-hosted model inference is an advantage.
• Strong product sense and curiosity about end users, with the ability to translate user needs into effective technical and product decisions.
• Excellent collaboration and communication skills, with a calm and thoughtful approach to solving complex problems in a fast-moving environment.
• Ability to take ownership, work independently, make sound technical decisions, and drive projects forward with minimal oversight.
• Strong written communication and the ability to collaborate remotely with meaningful working-hour overlap across UK and US time zones.
• Experience in educational technology or early-childhood education is a plus.
• Additional experience with multilingual retrieval, video or audio machine learning, FERPA/COPPA, or similar privacy and compliance frameworks is advantageous.
• Applicants must have the right to work in India; visa sponsorship is not available.

Benefits

• Competitive, market-aligned salary for an experienced engineer in India.
• Fully remote, full-time employment with flexibility in how you structure your working day.
• End-to-end ownership of the AI capabilities behind a flagship product, from launch through scale.
• Significant influence over AI architecture, technical direction, and product roadmap.
• Opportunity to work at the intersection of education, media, artificial intelligence, and technology.
• Collaborative, family-friendly, and mission-driven working environment.
• Opportunity to build highly visible AI technology designed to create meaningful outcomes for educators and young learners.