| JOB TITLE: Full-Stack AI Application Engineer | |
| DEPARTMENT: Generative AI Products | |
| LOCATION: Remote | |
| ROLE OVERVIEW | |
| We are seeking an innovative Full-Stack AI Engineer to build intelligent web applications and production AI microservices. You will work on cutting-edge generative AI tools that combine modern frontend frameworks with structured Python backends. | |
| KEY RESPONSIBILITIES | |
| - Build and deploy high-performance REST APIs using Python FastAPI and Pydantic validation. | |
| - Develop responsive, dynamic web interfaces using Next.js and modern JavaScript/TypeScript. | |
| - Integrate large language models (Google Gemini API, OpenAI) with structured JSON schemas and reliable error handling. | |
| - Work collaboratively using standard Git workflows (feature branches, pull requests, daily commits). | |
| - Implement semantic vector search pipelines using Qdrant Vector Database. | |
| REQUIRED QUALIFICATIONS | |
| - Strong proficiency in Python and FastAPI for backend development. | |
| - Hands-on experience developing frontends with Next.js or React. | |
| - Demonstrated experience integrating structured LLM APIs (Gemini Flash or similar). | |
| - Experience writing clean, well-tested code with Git collaboration best practices. | |
| - Familiarity with Docker containerization is a strong plus. | |