GenAI Data Engineer
⚲ Warszawa
28 560 - 31 920 PLN netto (B2B)
Wymagania
- Python
- LLM
- RAG
- AI Agents
- Azure AI
- Azure AI Search
- Cosmos DB
- Databricks
- ETL / Data Pipelines
- Prompt Engineering
Opis stanowiska
Location: 100% remote work (Poland)
Availability: ASAP / within 1 month
Contract Type: B2B via Experis
Responsibilities
• Design and implement RAG pipelines including data retrieval, processing, and storage of results
• Build solutions using LLMs for classification and data processing
• Develop and enhance AI agents including multi-agent workflows, orchestration, tool usage, and memory
• Implement agent integrations including A2A, MCP, and integrations with tools and APIs
• Develop and optimize data pipelines including ETL, ingestion, and processing
• Design and implement prompt engineering, model evaluation, and guardrails mechanisms
• Deploy and maintain GenAI solutions in Azure environments
• Collaborate with Data, ML, and Product teams in a project-based model
Requirements
• Strong proficiency in Python including LLM integration and data pipelines
• Hands-on experience with RAG pipelines, LLM-based classification, and AI agent development
• Good understanding of the GenAI ecosystem including prompt engineering, model evaluation, guardrails, and memory & tools
• Experience with Azure AI stack including Azure AI Search, Cosmos DB, and Azure AI Foundry or model deployment
• Experience with Databricks including Mosaic AI or Agent Framework
• Ability to work in production environments including scaling, monitoring, and optimization
Nice to Have
• Knowledge of GCP in the context of data engineering including ETL, ingestion, and pipeline orchestration
• Experience working in multi-cloud environments
• Practical experience in cost and performance optimization of GenAI solutions
Offer
• Multisport card
• Private healthcare (Medicover)
• Access to an e learning platform
• Group life insurance
Availability: ASAP / within 1 month
Contract Type: B2B via Experis
Responsibilities
• Design and implement RAG pipelines including data retrieval, processing, and storage of results
• Build solutions using LLMs for classification and data processing
• Develop and enhance AI agents including multi-agent workflows, orchestration, tool usage, and memory
• Implement agent integrations including A2A, MCP, and integrations with tools and APIs
• Develop and optimize data pipelines including ETL, ingestion, and processing
• Design and implement prompt engineering, model evaluation, and guardrails mechanisms
• Deploy and maintain GenAI solutions in Azure environments
• Collaborate with Data, ML, and Product teams in a project-based model
Requirements
• Strong proficiency in Python including LLM integration and data pipelines
• Hands-on experience with RAG pipelines, LLM-based classification, and AI agent development
• Good understanding of the GenAI ecosystem including prompt engineering, model evaluation, guardrails, and memory & tools
• Experience with Azure AI stack including Azure AI Search, Cosmos DB, and Azure AI Foundry or model deployment
• Experience with Databricks including Mosaic AI or Agent Framework
• Ability to work in production environments including scaling, monitoring, and optimization
Nice to Have
• Knowledge of GCP in the context of data engineering including ETL, ingestion, and pipeline orchestration
• Experience working in multi-cloud environments
• Practical experience in cost and performance optimization of GenAI solutions
Offer
• Multisport card
• Private healthcare (Medicover)
• Access to an e learning platform
• Group life insurance
🔍 Dekoder Ogłoszenia
🔴
Design and implement RAG pipelines including data retrieval, processing, and storage of results
Oczekuje się, że będziesz projektować i wdrażać kompletne potoki RAG, a nie tylko korzystać z gotowych rozwiązań.
🟡
Build solutions using LLMs for classification and data processing
Może oznaczać zarówno tworzenie zaawansowanych modeli, jak i prostsze zastosowania API.
🔴
Develop and enhance AI agents including multi-agent workflows, orchestration, tool usage, and memory
Wymaga głębokiego zrozumienia i praktyki w budowaniu złożonych systemów agentów, a nie tylko podstawowej integracji.
🔴
Ability to work in production environments including scaling, monitoring, and optimization
Oczekiwana jest pełna odpowiedzialność za działanie rozwiązań w środowisku produkcyjnym, w tym rozwiązywanie problemów i zapewnienie wydajności.
🟡
Experience with Azure AI Foundry or model deployment
Może oznaczać pracę z gotowymi usługami Azure AI Foundry lub samodzielne wdrażanie modeli, co wymaga szerszych kompetencji.