Full-Stack Engineer (LLM & RAG Focus)

O projekcie: Project Description We are seeking a Mid–Senior Full-Stack Engineer with hands-on experience in Large Language Model (LLM) integrations to join a product-oriented engineering team. The role focuses on designing, implementing, and iterating AI-driven features, including Retrieval-Augmented Generation (RAG) pipelines. You will contribute across the full technology stack, working closely with backend and frontend components while continuously improving AI output quality through experimentation and evaluation. The environment emphasizes rapid iteration, feedback-driven development, and effective use of modern AI-assisted engineering tools. Wymagania: - 3–5 years of professional experience in software development - Strong programming skills in Python - Experience integrating Large Language Models (LLMs) into production workflows - Practical knowledge of Retrieval-Augmented Generation (RAG) architectures - Experience with React and/or Next.js - Understanding of API design and full-stack development principles - Ability to work in iterative, experiment-driven environments - Strong analytical mindset and focus on quality improvement Nice to Have - Experience with FastAPI - Hands-on work with LLM evaluation frameworks and prompt engineering - Experience measuring and improving AI output quality - Familiarity with AI coding assistants (e.g., Cursor, GitHub Copilot) - Ability to quickly adapt to feedback and evolving project requirements Codzienne zadania: - Design and implement end-to-end features across backend and frontend layers - Develop and iterate on LLM-based functionalities, including RAG pipelines - Integrate AI services and optimize prompt workflows for improved output quality - Collaborate on API design and ensure seamless frontend-backend communication - Contribute to frontend implementation using modern React-based frameworks - Support evaluation, testing, and continuous improvement of AI-generated outputs - Participate in experiment-driven development and iterative feature delivery - Work closely with team members to refine solutions based on feedback and metrics