Mid-Senior Full Stack Engineer – AI & RAG

Job Responsibilities - Build and own the full-stack development of an AI-powered SEO optimization platform. - Develop frontend, backend, APIs, database, and deployment independently. - Build SEO optimization features using LLMs, RAG, and knowledge-based retrieval. - Design and implement knowledge ingestion, embeddings, vector search, retrieval pipelines, and prompt workflows. - Develop features for content analysis, keyword optimization, metadata generation, content improvement, and SEO recommendations. - Integrate third-party APIs and relevant SEO data sources. - Design reliable backend workflows for LLM and retrieval-based processing. - Handle testing, debugging, performance optimization, and production deployment. - Work independently, make technical decisions, and take ownership from architecture through delivery. Qualifications - 3–5 years of professional full-stack development experience. - Strong hands-on experience with modern frontend and backend development. - Practical experience integrating LLMs and AI APIs into real applications. - Experience building RAG systems, including embeddings, retrieval, vector databases, chunking, and prompt engineering. - Experience with technologies such as React/Next.js, Node.js/Python/.NET, or equivalent. - Familiarity with vector databases such as pgvector, Pinecone, Qdrant, Weaviate, OpenSearch, or similar. - Strong understanding of APIs, databases, authentication, cloud deployment, and application architecture. - Basic understanding of SEO, content optimization, keywords, metadata, and search intent is preferred. - Able to take loosely defined requirements and turn them into a working product independently. - Strong problem-solving and debugging skills. - Comfortable working in a fast-moving startup environment with minimal supervision. - Immediate joiners only.