Informacje o stanowisku

We are looking for an experienced GenAI Engineer to build and scale backend services for AI-powered chat and agentic systems. The role combines strong backend engineering fundamentals with deep expertise in LLM integration, prompt engineering, and agentic workflow design , including data ingestion and retrieval pipelines

Responsibilities

• Design, build, and maintain backend services primarily in Python (with Go or Rust as a plus)

• Integrate and orchestrate LLMs for chat and agentic workflows

• Design and improve prompt engineering , prompt chaining, and tool/function calling

• Build data ingestion pipelines (parsing, normalization, chunking, enrichment)
  Implement and optimize RAG pipelines including embeddings, vector search, and reranking

• Work with PostgreSQL and vector databases (e.g., Qdrant)

• Develop scalable and reliable systems running on Kubernetes

• Contribute to system scalability and performance as well as bug fixing and stability

• Ensure observability, reliability, and clean engineering practices in production systems

Requirements

• 5+ years of experience as a backend engineer

• Strong proficiency in Python (FastAPI, Django, or similar frameworks)

• Hands-on experience with LLM-based systems (chatbots, assistants, agents)

• Experience with prompt engineering and agentic workflows

• Solid experience with RAG architectures , including chunking and reranking

• Experience with vector databases

• Strong understanding of backend system design and scalability

• Experience with Kubernetes and cloud-native architectures

• Experience with PostgreSQL

Nice to Have

• Experience with Go or Rust

• Familiarity with agent frameworks (LangChain, LlamaIndex, etc.)

• Experience with AI evaluation, monitoring, and observability

• Experience with high-load or real-time systems

Warszawa - Oferty pracy w okolicznych lokalizacjach