(Summary generated by AI based on the full job description)
The project focuses on building production AI systems outside Jupyter, delivering reliable, observable and cost-efficient services. The tech stack centers on Python, agent and orchestration frameworks like LangChain, LangGraph, Semantic Kernel, cloud AI/ML services on Azure/AWS/GCP, and vector databases with embedding models. Responsibilities include end-to-end knowledge-grounded AI: data ingestion, chunking, embedding pipelines, retrieval and re-ranking, building agentic apps with tool integrations and memory, implementing ML pipelines, optimizing model serving (API, batching, caching, GPU, cost), writing production-grade tested Python, and building evaluation and monitoring for quality and drift. Requires at least 4 years in ML engineering and fluency in Polish and English.

Optional



By clicking "Aplikuj" you confirm that you've read and accepted our Terms and Conditions.
Certain terms used in this advertisement result from the standard layout and functionality of the website. They are technical in n ...
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Need more information?