Full Stack AI Engineer

Full Stack AI Engineer. The ideal candidate should have strong expertise in both Applied AI/Generative AI and Full Stack Development. We are looking for someone who can independently design, develop, and deploy AI-powered applications, covering the complete lifecycle from AI integration and backend development to frontend implementation and cloud deployment. Please ensure the JD covers the following technical requirements: 1. Applied AI / Generative AI (Must Have) • Hands-on experience with LLMs, including OpenAI, Google Gemini, Anthropic, and open-source models (Hugging Face, etc.).. • Retrieval-Augmented Generation (RAG) and vector database integration.. • AI Agent development, tool calling, and function calling.. • Multi-agent architectures and Agent-to-Agent (A2A) communication.. • Model Context Protocol (MCP) and MCP server/tool development.. • Prompt engineering and context engineering.. • Frameworks such as LangChain and related AI orchestration frameworks.. • Building AI-powered workflows, intelligent tools, and autonomous agents.. 2. Frontend Development (Must Have) • React.js and Next.js.. • JavaScript.. • Tailwind CSS.. • Vite.. • Ability to build responsive, scalable, and user-friendly interfaces.. 3. Backend Development (Must Have) • Python.. • Django and Django REST Framework (DRF).. • FastAPI.. • Node.js.. • REST API development and third-party service integrations.. 4. Database & Storage (Must Have) • PostgreSQL.. • Qdrant.. • MySQL.. • Redis.. • Experience designing and optimizing relational and vector database solutions.. 5. DevOps & Cloud (Must Have) • AWS cloud services.. • Application deployment, hosting, and production management.. • Understanding of CI/CD, Docker, and cloud infrastructure.. 6. Good to Have • Experience with additional LLM providers and open-source AI models.. • Fine-tuning and evaluation of LLMs.. • AI observability, monitoring, and performance optimization.. • Kubernetes and infrastructure automation.. • Experience with scalable, distributed systems.. • Familiarity with emerging AI protocols, frameworks, and technologies.. Overall Expectation: We are looking for a strong Full Stack AI Engineer who understands the AI ecosystem deeply and can translate AI capabilities into production-ready applications. The candidate should be comfortable working across AI engineering, frontend, backend, databases, and cloud infrastructure. Important: All technologies explicitly listed under the Must Have sections should be treated as required skills, while additional relevant technologies can be included under Good to Have. Requirements 1. Applied AI / Generative AI (Must Have) Hands-on experience with LLMs, including OpenAI, Google Gemini, Anthropic, and open-source models (Hugging Face, etc.). Retrieval-Augmented Generation (RAG) and vector database integration. AI Agent development, tool calling, and function calling. Multi-agent architectures and Agent-to-Agent (A2A) communication. Model Context Protocol (MCP) and MCP server/tool development. Prompt engineering and context engineering. Frameworks such as LangChain and related AI orchestration frameworks. Building AI-powered workflows, intelligent tools, and autonomous agents. 2. Frontend Development (Must Have) React.js and Next.js. JavaScript. Tailwind CSS. Vite. Ability to build responsive, scalable, and user-friendly interfaces. 3. Backend Development (Must Have) Python. Django and Django REST Framework (DRF). FastAPI. Node.js. REST API development and third-party service integrations. 4. Database & Storage (Must Have) PostgreSQL. Qdrant. MySQL. Redis. Experience designing and optimizing relational and vector database solutions. 5. DevOps & Cloud (Must Have) AWS cloud services. Application deployment, hosting, and production management. Understanding of CI/CD, Docker, and cloud infrastructure. 6. Good to Have Experience with additional LLM providers and open-source AI models. Fine-tuning and evaluation of LLMs. AI observability, monitoring, and performance optimization. Kubernetes and infrastructure automation. Experience with scalable, distributed systems. Familiarity with emerging AI protocols, frameworks, and technologies. Overall Expectation: We are looking for a strong Full Stack AI Engineer who understands the AI ecosystem deeply and can translate AI capabilities into production-ready applications. The candidate should be comfortable working across AI engineering, frontend, backend, databases, and cloud infrastructure. Important: All technologies explicitly listed under the Must Have sections should be treated as required skills, while additional relevant technologies can be included under Good to Have.