Full-Stack Engineer (AI-Powered Platform)

Full-Stack Engineer (AI-Powered Platform) We’re looking for a Full-Stack Engineer with strong AI literacy to build and scale the web applications behind our AI-driven research platform. You’ll work end-to-end — from responsive frontend interfaces to backend services and LLM integrations. Responsibilities Build responsive web interfaces for AI features such as report generation, expert matching, and real-time dashboards Develop and maintain REST APIs with Java (Spring Boot) and Python (FastAPI) Integrate LLMs (OpenAI, Claude via AWS Bedrock) into production workflows Implement RAG-based features, semantic search, and AI-powered recommendations Deploy and manage services on AWS (ECS, Lambda, S3, RDS) Work with PostgreSQL and vector databases (Qdrant) Ensure reliability with logging, monitoring, and CI/CD pipelines Requirements 2+ years of full-stack development experience Strong frontend skills ( React, Angular, or Vue ) Backend experience with Java Spring Boot Good knowledge of Python Experience with AWS, Docker, and REST APIs Experience integrating AI/ML models or LLM APIs Nice to Have Experience with RAG architectures and semantic search Knowledge of LangChain, LangGraph, or agent frameworks Experience with vector databases (Qdrant, Pinecone, Weaviate) Tech Stack React/Angular • TypeScript • Java Spring Boot • Python FastAPI • AWS • PostgreSQL • Qdrant • Docker • CI/CD What We Offer High-impact role in a small, fast-moving team Ownership from feature design to deployment Work with modern AI technologies and LLMs Remote-first environment