AI Engineer (LLM & Agents)

Do you want to work in a highly dynamic environment? Are you passionate about turning business problems into AI‑powered products? You have deep expertise in building AI, using the latest LLMs and AI Agents to solve complex problems in a creative way? Then our Data Science & AI team wants to hear from you! Join us in shaping the future of financial information. We are building a next-generation, AI-powered agent deeply integrated into our information terminal, redefining how users explore, analyze, and interact with complex financial data. If you are passionate about agentic AI, enjoy solving hard engineering problems, and want to see your work used daily by real users in a critical product, this is a unique opportunity to have a tangible impact from day one.

What You Will Do

• Architect Multi-Agent Systems: Design, build, and orchestrate complex agentic workflows using LangGraph and LangChain to handle sophisticated financial queries.

• Engineer Robust Tool Interfaces: Develop and maintain reliable tool definitions for interacting with complex internal APIs, ensuring the AI can accurately parse, validate, and utilize financial data.

• Implement Advanced RAG: Build and optimize Retrieval-Augmented Generation systems to ground model responses in proprietary data.

• Drive Structured Output Generation: Ensure AI responses are structured for rich UI rendering, enabling the generation of dynamic graphs, charts, and interactive elements.

• Establish Evaluation Pipelines: Create rigorous testing frameworks and metrics to evaluate agent performance, reliability, and accuracy in a production environment.

What You Bring 

• 5+ years of experience as Data Scientist, or 2+ as a Gen AI Application Developer. 

• Core AI Engineering Stack: Deep expertise in Python and the modern AI stack, including LangChain, LangGraph, OpenAI SDK, and Hugging Face Transformers. Strong ability to debug and optimize multi-agent workflows, with a focus on asynchronous execution, state management, and concurrency.

• API & Data Proficiency: Experience designing and integrating with complex REST/GraphQL endpoints and handling structured data formats (JSON/XML) for tool calling.

• Cloud & DevOps Mindset: Hands-on experience with containerization (Docker) and cloud platforms (AWS/GCP/Azure) for deploying production-grade AI applications.

• Vector Search Knowledge: Familiarity with vector databases (Pinecone, Weaviate, Chroma) and embedding strategies for semantic search and RAG implementation.

• Hybrid work 3 days/week from Madrid or Warsaw.

• Fluent in English (both verbal & writing).