AI Engineer

Scalo is a company delivering software projects and supporting partners in business development. Their activities include technology consulting, software development, embedded systems, cloud solutions, data management, and dedicated project teams.

• Very good knowledge of Java and/or Python
• Practical experience building solutions using Large Language Models (LLM)
• Familiarity with at least one AI framework (e.g., LangChain4j, Google ADK, Pydantic AI, Spring AI)
• Knowledge of Google BigQuery, including SQL, data modeling, cost and performance optimization
• Experience creating services and integrating REST API
• Ability to test and diagnose LLM-based systems
• Good software engineering practices and readiness to develop competences in Chat with Data, unstructured data, and AI

Nice to have:

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

• Develop and enhance Chat with Data solution for natural language queries on data
• Design and implement mechanisms to interpret user intents and safely generate executable queries
• Develop AI solutions using LLMs and AI frameworks like LangChain4j, Google ADK, Pydantic AI, or Spring AI
• Integrate language models with data and backend services
• Use Google BigQuery for data analysis, SQL query creation, and performance and cost optimization
• Test and evaluate response quality of LLM-based solutions
• Develop Unstructured Data Repository (UDR) platform for the processing, storage, and sharing of unstructured data
• Collaborate on processing documents, images, and audio including OCR, ASR, content extraction, and embeddings
• Design and develop services and integrations using REST API
• Analyze and troubleshoot issues in GenAI systems
• Address security, quality, and reliability in AI solutions
• Participate in Artificial Intelligence Formation initiatives (P0148)
• Service model: hybrid with 1 day per week in Warsaw office

Work model is hybrid with 1 day per week in the office in Warsaw