Dataiku is the enterprise platform for AI success. As a Senior Generative AI Engineer on the ED&A team you build the agentic AI systems that change how Dataiku runs internally. The role is hands-on and end-to-end: you work close to the business (primarily the Revenue organisation - Sales, BDR, Customer Success, Solutions Engineering, Professional Services, Sales Ops and Marketing, ~75% of the role), turn real problems into working software, and own projects from first conversation to production. The role is remote in the United Kingdom.
Responsibilities
- ▹Design end-to-end AI solutions on Dataiku's platform (Agent Hub, Prompt Studio, LLM Mesh, Knowledge Banks/Vector Stores) or Python-based frameworks where needed
- ▹Build and orchestrate multi-agent systems using Dataiku Visual Agents and code-based frameworks (LangGraph, CrewAI, Claude Agent SDK, OpenAI Agents SDK)
- ▹Integrate and optimize LLM APIs across providers (OpenAI, Anthropic, Google Gemini, AWS Bedrock, Azure, open-source via LLM Mesh) with model routing for cost, latency and quality
- ▹Implement RAG pipelines including agentic RAG and GraphRAG with reranking, dynamic filtering and document extraction
- ▹Develop autonomous and semi-autonomous AI agents and build Agent Tools (custom API integrations, data retrieval, decisioning logic, automated workflows)
- ▹Build, publish and consume MCP (Model Context Protocol) servers for agent-to-tool integration, including custom MCP servers
- ▹Design and maintain evaluation frameworks (evals) measuring accuracy, latency, cost and reliability in production
- ▹Adhere to data governance, security and regulatory compliance (EU AI Act awareness, responsible AI) and use Dataiku's Cost Guard and Quality Guard
- ▹Create front-end UIs for AI applications using HTML, CSS, JavaScript (Dataiku webapps, Dataiku Answers, or standalone apps with Vue.js and Node.js)
- ▹Engage stakeholders, gather requirements and identify the underlying user pain; provide product feedback and stay current with the evolving AI landscape (MCP, A2A protocols)
Requirements
- ▹Strong Python skills, including typical data science and AI engineering libraries
- ▹Hands-on experience building agentic AI systems: multi-agent orchestration, tool chaining, autonomous decision-making and production deployment of AI agents
- ▹Experience with modern agent orchestration frameworks (LangGraph, CrewAI, Claude Agent SDK, OpenAI Agents SDK); LangChain familiarity relevant but not sufficient alone
- ▹Understanding of RAG architectures (vector databases, embedding strategies, agentic RAG, GraphRAG) and when to apply each
- ▹Familiarity with MCP for agent-to-tool integration, or the ability to quickly adopt new integration standards
- ▹Experience with structured outputs, function/tool calling and prompt engineering across multiple LLM providers
- ▹Web development fundamentals (HTML, CSS, JavaScript)
- ▹Exposure to AI evaluation practices: building evals, monitoring model/agent performance and iterating on metrics
- ▹Bachelor's or Master's in Computer Science, Data Science, Engineering or a related field; equivalent experience considered
Nice to have
- ▹Experience with Vue.js and Node.js
- ▹Comfort with AI-assisted development tools (GitHub Copilot, Cursor, Claude Code or similar)
- ▹Familiarity with Dataiku
Soft skills
Strong communication and presentation skills with technical and non-technical stakeholdersProblem-solving mindset and passion for delivering measurable business valueOpenness to learning new tools and adapting to a rapidly evolving AI landscape
Education: Bachelor's or Master's in Computer Science, Data Science, Engineering, or a related field; equivalent experience also considered