The project focuses on the development of modern applications using generative artificial intelligence and large language models in a production environment. It includes the design of the AI solution architecture, their integration into backend and frontend systems, and optimization of performance and scaling. The development takes place in a small agile team with an emphasis on best practices (testing, CI/CD, code review) and practical use of AI for real business scenarios. The work also includes working with prompts and debugging models, creating chatbots or assistants, and implementing APIs and cloud services so that the AI solution works reliably and long-term in production.

• End-to-end development: Design and development of Gen AI applications in Python from architecture to performance optimization.
• Fullstack overlap: Implementation of front-end interactions in React (TS) and creation of robust API endpoints on the backend.
• LLM & RAG: Integration and debugging of LLM models, advanced Prompt Engineering and working with LangChain.
• Scaling: Designing strategies for effective deployment and scaling of Gen AI in production environments.
• Modern Ops: Working in the cloud (Azure/AWS/GCP) with an emphasis on CI/CD, testing and code review.

• Experience with design and development of AI applications (LLM, NLP, chatbots).
• Strong Python (Django, FastAPI or Flask).
• Experience with React (TypeScript) or Next.js.
• Ability to design cloud-based application architecture.
• English B2 (communication with clients worldwide).

Advantage

• Experience with LangChain and MLOps (model deployment).
• DevOps knowledge (Docker, K8s, Terraform/Bicep).
• Knowledge of Serverless computing (Azure Functions, AWS Lambda).

• Great colleagues and fully flexible work policy
• Career coaching and development
• Flexible working hours
• Technical training and workshops
• Technical equipment for work (Mac / Windows)
• Company parties
• Company psychologist for mental well-being
• Multisport card