GenAI Engineer – Conversational Analytics

PKO Finat Sp. z o.o. works on an AI solution enabling natural language queries over data and an Unstructured Data Repository platform for processing and sharing unstructured data like documents, images, and audio for AI use.

• Very good knowledge of Java and/or Python
• Practical experience building solutions with large language models (LLMs)
• Familiarity with at least one framework such as LangChain4j, Google ADK, Pydantic AI, or Spring AI
• Knowledge of Google BigQuery including SQL, data modeling, cost, and performance optimization
• Experience creating services and integrating REST APIs
• Ability to test and diagnose systems based on LLMs
• Understanding of best practices for software creation, deployment, and maintenance

Nice to have:

• Experience with NL2SQL, conversational analytics, or BI-as-chat solutions
• Knowledge of RAG, embeddings, chunking, and re-ranking techniques
• Experience processing documents, images, or audio including OCR, text extraction, and transcription
• Experience evaluating GenAI systems with offline and online tests, and prompt versioning
• Knowledge of semantic or metrics layers, caching, and pre-aggregation
• Familiarity with MCP and agent architectures
• Experience with vector databases like Qdrant, Pinecone, Weaviate, or Milvus
• Knowledge of graph databases like Neo4j and the GraphRAG approach
• Familiarity with FastAPI, Kubernetes, Cloud Run, and Pub/Sub
• Knowledge of Rust
• Experience in regulated environments covering audit, data classification, access control, and sensitive data protection

• Design and develop the "chat with data" solution, focusing on NL2SQL mechanisms and conversational analytics
• Build services using large language models and integrate models with corporate data and systems
• Implement safeguards to limit hallucinations, incorrect queries, and unauthorized data access
• Develop RAG solutions including chunking, embeddings, semantic search, and re-ranking
• Design tests and evaluations for GenAI solution quality
• Optimize quality, performance, and cost of BigQuery queries
• Create services and API integrations in Java and/or Python
• Support the Unstructured Data Repository for processing documents, images, and audio, including content and metadata extraction
• Integrate AI models with unstructured data processing workflows
• Deploy, monitor, and maintain solutions following DevSecOps practices

Forma współpracy: B2B. Work mode is hybrid (office and remote).