Full Stack AI Engineer

Responsibilities Build and maintain web applications, APIs, and services using Python. Develop and improve AI applications using large language models (LLMs), including Retrieval-Augmented Generation (RAG) solutions. Design document-ingestion, chunking, embedding, retrieval, and response- generation workows. Design and develop tools for AI applications, including function-calling workows and integrations using the Model Context Protocol (MCP). Integrate vector databases and search technologies into production systems. Develop responsive frontend features and connect them to backend APIs. Evaluate AI output quality, retrieval relevance, latency, and cost; improve performance and reliability. Implement authentication, authorization, logging, testing, and monitoring. Apply software engineering best practices, including SOLID principles and design patterns, to build scalable, maintainable systems. Deploy and operate LLMs in on-premises environments using inference servers such as vLLM or SGLang. Collaborate with product, design, and engineering teams to turn requirements into production-ready features. Document technical decisions and contribute to code reviews and engineering standards. Required Qualications Professional experience developing full-stack web applications. Strong Python skills and experience with frameworks such as FastAPI, Django, or Flask. Experience designing and building REST APIs or similar service interfaces. Hands-on experience developing LLM-powered applications and RAG workows. Familiarity with function calling, MCP, and designing or developing tools for AI applications. Familiarity with embeddings, vector search, prompt design, and document- processing pipelines. Experience with a relational database such as PostgreSQL and at least one vector database or vector-search solution.

Frontend experience with JavaScript or TypeScript and a modern framework such as React. Familiarity with Git, automated testing, deployment workows, and software engineering best practices. Strong problem-solving, communication, and collaboration skills. Preferred Qualications Experience with cloud platforms such as AWS, Azure, or Google Cloud. Familiarity with Docker, CI/CD, and production observability. Experience deploying LLMs on-premises, including using inference servers such as vLLM or SGLang. Experience with LLM evaluation, guardrails, hybrid search, reranking, or agentic workows. Experience handling sensitive data and implementing security and privacy controls. Contributions to technical projects, open-source software, or developer communities.