Senior Full-Stack Developer

About the role
We are looking for a Senior Full-Stack Developer who can take a product from idea to production. You will build backend and frontend, own deployment and infrastructure, and use AI coding agents to ship faster without cutting corners on quality. You won't just pick up tasks: you'll shape the architecture, build the solution, deploy it, monitor it, and own it technically.
What you'll do
• Full-stack engineering: Design and build backend services, APIs, frontends and dashboards; model data; integrate internal and external services; debug and tune performance.
• AI features: Turn LLM, RAG and AI-agent capabilities into production-ready services, connected to APIs, databases and internal tools, using both cloud and local models.
• DevOps and infrastructure: Dockerize services, maintain CI/CD pipelines, manage servers, environments and secrets, and set up monitoring and logging.
• Production ownership: Troubleshoot live issues, improve reliability, and help shape cloud and on-premise architecture.
• AI-assisted development: Use Claude Code, Codex, Cursor, Copilot or similar tools across the full loop: problem, architecture, task breakdown, AI coding, review, test, debug, deploy.
What you bring
• 5+ years of professional software engineering, with real backend and frontend experience
• Strong skills in at least two backend stacks: .NET/C#, Python, or Node.js/TypeScript
• Experience with a modern frontend framework: React, Next.js, or Vue/Nuxt
• Solid SQL and database design; REST APIs and service architecture
• Hands-on Git, CI/CD, Docker, Linux and server management
• Practical knowledge of LLMs, RAG, AI agents, embeddings, vector search and tool calling
• Professional, daily use of AI coding tools, and the judgment to validate their output
Beyond the stack, we care most about problem solving, ownership from design to production, fast learning, and knowing when to rely on AI and when to decide yourself.
Nice to have
• Production experience with LLMs, AI agents, RAG or vector databases
• Deploying AI models or GPU services; open-source LLMs and local AI
• Kubernetes and cloud platforms (Azure, AWS or GCP)
• RabbitMQ or other message queues; Redis and caching
• Event-driven or microservice architectures
• Monitoring with Grafana, Prometheus or Zabbix
• Work in product-focused or Agile teams