





Login to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Remote, mid-level, metro preference and broad appealing full-stack/AI scope increases applicant density.
Requires production LLM, RAG, and AI-native engineering skills, limiting cross-industry transferability.
Explicit 5+ years plus mandatory production LLM, RAG, and AWS/backend/frontend skills create strict filters.
Own the AI behind Audrey, including retrieval, generation, and logic models, ensuring fast, accurate, and reliable content discovery for educators.
Develop and maintain end-to-end content and data pipelines integrating videos, printables, guides, and multilingual content for precise AI-driven retrieval.
Collaborate across backend and frontend teams to launch and continually improve Audrey, shaping AI behavior, user experience, and product roadmap with compliance to privacy standards like FERPA/COPPA.
5+ years software engineering experience across full stack (backend and frontend).
Proven hands-on experience building and shipping at least one production LLM/AI application, including retrieval-augmented systems with embeddings, vector databases, and semantic search.
Strong Python skills, backend fundamentals (APIs, databases, data pipelines), and practical LLM orchestration/prompt engineering experience (e.g., LangChain).
Must be India-based with legal work authorization; Remote role with required overlap with UK/US time zones.
AI-native full-stack engineer fluent in modern AI-assisted development tools, able to build rapidly across AI workflows.
Strong product sensibility with curiosity about end-users (early childhood educators) and a collaborative working style with transparent communication.
Experienced with cloud infrastructure (AWS preferred), LLM orchestration, and building scalable AI products compliant with educational privacy regulations.