AI Engineer (GenAI / RAG / Agentic AI)

Kyotu Technology is a boutique software house based in Wrocław and Warsaw, working fully remotely or in hybrid mode across Poland. They focus on long-term, high-quality engineering and building complex, production-grade systems with real business impact. Their teams have real influence on technical and architectural decisions.

• minimum 4 years of commercial experience in Python development (FastAPI, async programming)
• hands-on experience with GenAI and LLM-based systems
• experience building RAG solutions (retrievers, vector search, hybrid search)
• experience with prompt engineering and LLM orchestration frameworks (e.g. LangChain, LlamaIndex)
• experience with at least one LLM platform/provider (Azure OpenAI, AWS Bedrock, OpenAI API)
• experience with PostgreSQL and vector databases (e.g. pgvector, Qdrant)
• basic knowledge of ElasticSearch/OpenSearch
• experience with Docker and cloud platforms (AWS or Azure)
• understanding of Kubernetes/OpenShift fundamentals
• experience with CI/CD, testing, Git, and code review processes
• understanding of observability, logging, metrics, and tracing
• understanding of security fundamentals (OIDC/OAuth2, secrets management, PII protection)
• ability to optimize latency, scalability, and operational costs
• strong engineering mindset and ownership attitude
• Polish and English at B2 level or higher

Nice to have:

• experience with agentic AI systems and multi-agent workflows
• experience in banking or enterprise environments
• experience with OpenTelemetry and distributed tracing
• knowledge of ML evaluation methodologies and RAG regression testing

• design and implement GenAI applications, including RAG systems and agentic workflows
• build and maintain AI pipelines (chunking, embeddings, indexing, hybrid search, reranking)
• develop APIs and serving layers using FastAPI
• evaluate and monitor quality, latency, and cost of AI solutions
• implement guardrails, content filtering, PII protection, and prompt security mechanisms
• integrate AI services with enterprise systems (REST, gRPC, ESB/EventBus)
• implement observability, logging, tracing, and monitoring solutions
• optimize system performance and infrastructure costs
• participate in code reviews, architecture discussions, and technical documentation
• collaborate with cross-functional engineering and business teams