... for enterprise platforms. Responsibilities Design and deploy production-grade Retrieval-Augmented Generation (RAG) systems using LangChain or LangGraph and vector databases Build and orchestrate LLM-based conversational AI and chatbots for enterprise-scale environments Architect AI agent workflows applying best practices ...
Poland, Warszawa
Zobacz ofertę... for enterprise platforms. Responsibilities Design and deploy production-grade Retrieval-Augmented Generation (RAG) systems using LangChain or LangGraph and vector databases Build and orchestrate LLM-based conversational AI and chatbots for enterprise-scale environments Architect AI agent workflows applying best practices ...
Poland, Kraków
Zobacz ofertę... for enterprise platforms. Responsibilities Design and deploy production-grade Retrieval-Augmented Generation (RAG) systems using LangChain or LangGraph and vector databases Build and orchestrate LLM-based conversational AI and chatbots for enterprise-scale environments Architect AI agent workflows applying best practices ...
Poland, Wrocław
Zobacz ofertę... for enterprise platforms. Responsibilities Design and deploy production-grade Retrieval-Augmented Generation (RAG) systems using LangChain or LangGraph and vector databases Build and orchestrate LLM-based conversational AI and chatbots for enterprise-scale environments Architect AI agent workflows applying best practices ...
Poland, Wrocław
Zobacz ofertę160 zł PLN - 180 zł PLN
... pipelines covering training, validation, inference, monitoring, and continuous improvement Deploy and scale AI workloads using Docker and Kubernetes Work with vector databases and graph databases for semantic retrieval and reasoning Integrate AI services with APIs, microservices, and cloud platforms such as AWS, Azure, or ...
Poland, Wrocław
Zobacz ofertę- Zdalnie
- Hybrydowo
- Pełny etat
3k
... engineering fundamentals (testing, CI/CD, code reviews). Proven experience building and deploying LLM applications in production, including RAG, embeddings, vector search, and model versioning. Experience with model training and evaluation (PyTorch, scikit-learn), including reproducible pipelines and experiment tracking. ...
Poland, Wrocław
Zobacz ofertę- Zdalnie
- Hybrydowo
- Pełny etat
- Kontrakt
25200 zł
... framework. Experience working with LLM SDKs (Anthropic, OpenAI). Experience implementing MCP (Model Context Protocol) servers and/or clients. Experience with vector databases (pgvector, Qdrant, Weaviate, Pinecone) and PostgreSQL, including hybrid search. Polish language at C2 (native) level. Nice-to-have: Experience with ...
Poland, Warszawa
Zobacz ofertę- Zdalnie
- Hybrydowo
- Stacjonarnie
... Databases – Snowflake, Azure Synapse Analytics, Amazon Redshift, GCP BigQuery - Relational SMP Databases – Azure SQL PaaS, MySQL, Oracle, PostgreSQL, SQL Server - Vector Databases & Semantic Search – Azure AI Search (Vector Search), ElasticSearch, Pinecone, Weaviate, FAISS, Milvus, semantic retrieval for RAG architectures What ...
Poland, Wrocław
Zobacz ofertę... environments. - Understanding of AI/ML technologies, including LLMs, Generative AI, and AI-powered application development; familiarity with RAG architectures, vector databases, and AI development tools (e.g., GitHub Copilot, Claude Code) is a plus. - Proven ability to lead Agile software delivery, balancing technical excellence, ...
Poland, Kraków
Zobacz ofertę... creating dashboards in Looker Studio or similar tools, Basic understanding of modern information retrieval mechanisms and LLM technologies, including embeddings, vector search, retrieval, and RAG, Confidence in using AI and APIs for work automation, such as LLM APIs, GSC API, GitHub, Python/JavaScript, or AI coding tools, Ability ...
Poland, Łódź
Zobacz ofertę... Next.js. Working knowledge of LLMs, prompt engineering, fine-tuning, and retrieval-augmented generation (RAG). Experience connecting to GenAI APIs and managing vector databases (FAISS, Pinecone, Weaviate, etc.). Familiarity with cloud platforms (AWS, Azure, GCP) and CI/CD pipelines for deploying AI-driven applications. Understanding ...
Poland, Warszawa
Zobacz ofertę100 - 150 zł / stawka godzinowa
... Warszawa Technologie, których używamy Wymagane - Google Cloud Platform - Vertex AI - Git - Python - LLM - GenAI - Agentic AI - LangChain - LangGraph - Vector DB Mile widziane - CI/CD - LLMOps - Evaluation O projekcie Poszukujemy osób z doświadczeniem w obszarze Google Cloud Platform oraz Data Science/AI, które ...
Poland, Warszawa
Zobacz ofertę160 zł PLN - 180 zł PLN
... pipelines covering training, validation, inference, monitoring, and continuous improvement Deploy and scale AI workloads using Docker and Kubernetes Work with vector databases and graph databases for semantic retrieval and reasoning Integrate AI services with APIs, microservices, and cloud platforms such as AWS, Azure, or ...
Poland, Wrocław
Zobacz ofertę25000 zł
... rozwijanie i wdrażanie funkcjonalności wykorzystujących LLM oraz machine learning, m.in. w oparciu o OpenAI API, budowanie systemów wykorzystujących RAG, embeddings, vector search, tool/function calling oraz agentic workflows, trenowanie, ewaluacja i wdrażanie modeli ML, wraz z przygotowaniem i przetwarzaniem danych potrzebnych ...
Poland, Warszawa
Zobacz ofertę- Zdalnie
- Hybrydowo
- Stacjonarnie
- Pełny etat
30240 zł
... pracy Technologie/tematy na projekcie: AWS, Azure, Kubernetes, Docker, Terraform, Helm, GitOps, LiteLLM lub podobny LLM Gateway, model serving/inference, API, vector storage/retrieval, caching, observability/monitoring/tracing, secrets management, IAM/access control Do Twoich głównych obowiązków na tym stanowisku należeć ...
Poland, Łódź
Zobacz ofertę... engineering practices (modular design, testing, code reviews) - Hands-on experience with LLM frameworks such as LangChain, LangGraph, or LlamaIndex - Experience with vector databases (e.g., Pinecone, Weaviate, pgvector, OpenSearch) - Practical experience building RAG pipelines and working with unstructured data - Experience working ...
Poland, Warząchewka Polska
Zobacz ofertę20240 - 25300 zł
... Hands-on with Generative AI: embeddings, prompt engineering, tool/function calling, and agent frameworks (LangChain, LangGraph, PydanticAI); experience with vector databases (pgvector and others). Solid grounding in classical ML: model selection, validation, and metrics (e.g., AUC/F1/RMSE); time series or forecasting experience ...
Poland, Warszawa
Zobacz ofertę420k
... development—where they provide measurable value. Your tasks Design and build GenAI applications (cloud/on‑prem) using LLMs and cloud services. Implement RAG patterns, vector search, and prompt orchestration. Integrate with client systems (APIs, events/queues) and automate CI/CD (Azure DevOps/GitHub Actions). Enable AI‑assisted engineering ...
Poland, Gdańsk
Zobacz ofertę... Functional Calling, and A2A within Azure environments. - Engineer prompts and contexts for optimal model performance. - Work with real-time data integration, vector databases, and embedding/chunking strategies. - Evaluate and optimize AI model outputs for accuracy and efficiency. Requirements - Strong experience in Java ...
Poland, Warząchewka Polska
Zobacz ofertę- Zdalnie
- Hybrydowo
- Stacjonarnie
- Kontrakt
25200 - 27720 zł
... widziane: Quarkus / GraalVM. Doświadczenie w tworzeniu własnych Kafka Connect connectorów, converterów lub SMT. Prometheus, Grafana, OpenTelemetry, Dynatrace, ELK/Vector. Kubernetes i rozwiązania chmurowe. Doświadczenie w optymalizacji wysokowydajnych systemów przetwarzania zdarzeń. Oferujemy: Długofalowe stabilne zatrudnienie ...
Poland, Wrocław
Zobacz ofertę