Senior GenAI Engineer - Dataiku
Ernst and Young3 days ago
Katowice, PolandSenior
Responsibilities
- Design, develop, and productionize LLM-based applications, RAG systems, and agentic AI solutions.
- Build and operationalize data science, machine learning, and GenAI solutions using Dataiku DSS.
- Experiment with modern AI architectures and tailor approaches to complex business use cases.
- Evaluate and optimize models, prompts, retrieval pipelines, response quality, groundedness, hallucination rate, latency, token usage, and cost.
- Design RAG architectures involving chunking, embeddings, vector search, retrieval strategies, reranking, and LLM integration.
- Implement MLOps and LLMOps practices including versioning, automated testing, deployment, evaluation, monitoring, logging, and observability.
- Integrate AI solutions through APIs and enterprise applications while addressing security, privacy, access control, prompt injection, and data leakage concerns.
- Collaborate with data scientists, software engineers, cloud and DevOps teams, business stakeholders, and operations teams.
- Translate complex business requirements into scalable, secure, and production-ready AI solutions.
Requirements
- At least 3 years of hands-on experience in Data Science, Machine Learning, and Artificial Intelligence.
- Strong practical experience in Generative AI, LLM-based applications, and agentic AI.
- Strong hands-on experience with Dataiku DSS, including building pipelines, developing and deploying models, and operationalizing AI or GenAI solutions.
- Strong proficiency in Python and experience with PyTorch, TensorFlow, Pandas, and Scikit-learn.
- Experience with at least one GenAI or agentic framework such as LangChain, LangGraph, AutoGen, or Semantic Kernel.
- Practical experience designing RAG architectures and applying NLP techniques including tokenization, text similarity, embeddings, semantic search, and information extraction.
- Experience with at least one major cloud platform: Azure, AWS, or GCP.
- Bachelor’s or Master’s degree in Computer Science, Engineering, or a related field.
- Hands-on experience with Docker, Kubernetes, Git, and CI/CD platforms such as Azure DevOps or GitHub Actions is preferred.
- Experience implementing MLOps and LLMOps practices, evaluating LLM applications, and implementing monitoring, logging, and observability is preferred.
- Knowledge of Responsible AI and Trusted AI practices, including safety, fairness, transparency, explainability, and accountability.
- Experience with vector databases or vector search technologies is preferred.
- Strong problem-solving, analytical, communication, and cross-functional collaboration skills.
Benefits
- Hybrid work arrangement in Katowice: two days in the office and three days remote.
- Continuous learning, skills development, coaching, and career support through EY’s global delivery network.
- Opportunity to work on global projects with well-known brands and teams across multiple EY service lines and geographies.
- Diverse and inclusive culture with flexibility to make a meaningful impact.
Tech Stack
AWSAzureDockerGitGitHub ActionsGoogle Cloud PlatformKubernetesPandasPythonPyTorchscikit-learnTensorFlow
Categories
About Ernst and Young
Ernst & Young (EY) provides audit/assurance, tax, consulting, strategy and transactions services to enterprises, financial institutions, and public‑sector clients. Structured as a global network of partner‑owned member firms, it sells professional services on a fee basis, including a dedicated Financial Services Organization for banking, insurance, and capital markets. Headquartered in London, EY was formed in 1989 from the merger of Ernst & Whinney and Arthur Young, and operates in 150+ countries.