Challenge yourself and us
At AdvanceWorks, we learn together, grow together, and have fun together. And we do all this while creating great software solutions for clients across many industries and geographies.
We are constantly challenging ourselves and each other to use the latest technologies and the best methodologies and make sure we walk the talk.
Exciting as it may sound, we also have our red lines: each of us is a unique person, with unique opinions, beliefs, options, interests, hopes, and fears. With the right to speak their mind, mindful about the common goals, and always being constructive.
It is the way we respect each other, discuss different points of view, challenge ourselves and each other, while tackling our common challenges, that makes us strong. United. Brave. And sure that there will be a better tomorrow, even when we make mistakes. Because we learn from both our failures and our successes.
What will be your role
We are looking for a Senior GenAI Engineer with strong expertise in Python, Azure, and production-grade LLM/RAG systems to design and build multi-agent generative AI architectures for one of the most innovative clients in the banking sector. This is not a chatbot scripting role. You will work on autonomous AI agents, retrieval pipelines, reasoning workflows, and observability systems, delivering robust, scalable, and reliable GenAI solutions.
Your responsibilities will include
* Design, build, and optimize multi-agent RAG orchestration systems
* Develop production-grade LLM-powered applications using Python
* Improve retrieval accuracy through index design, hybrid search, reranking, and score fusion
* Build and maintain asynchronous knowledge ingestion pipelines
* Reduce hallucinations using prompting, agent planning, grounding, and tool integration
* Deploy and operate solutions in Microsoft Azure, including Azure OpenAI, Azure AI Search, vector databases, Blob Storage, App Insights, and containerized services
* Implement observability and performance monitoring
* Ensure reliability, scalability, evaluation, and performance of AI systems in production
* Translate business requirements into robust AI system architectures
* Document architecture and mentor engineers
What should you bring to the team
* 4+ years of professional experience in AI/ML or backend engineering, building LLM/RAG systems in production
* Strong proficiency in Python (async/await, OOP, typing, design patterns)
* Experience with multi-agent orchestration frameworks (AutoGen, LangGraph, Semantic Kernel, or similar)
* Deep understanding of retrieval pipelines, embeddings, vector search, chunking, hybrid retrieval, reranking, and index design
* Practical experience with Azure AI stack (Azure OpenAI, Azure AI Search or vector DBs, Blob Storage, App Insights, container deployments)
* Experience deploying containerized services (Docker)
* Experience designing APIs, asynchronous systems, and service integrations
* Ability to debug hallucinations, retrieval failures, and agent orchestration issues
* Experience delivering production-ready AI systems
* Excellent communication skills and ability to collaborate with stakeholders
* Availability to work hybrid in Lisbon
What is in it for you
* An amazing informal culture of smart, hardworking, and friendly people who support and care about each other
* A mentorship program from day one
* Opportunity to influence strategic AI initiatives in high-visibility projects
* Formal training and certifications in Gen AI, cloud, and engineering excellence
* Access to cutting-edge tools and resources in AI and cloud computing
* A dynamic company where your ideas matter more than job titles
* Flexibility with responsibility
* Happy hours and feel-good after-hours events
* A Rubber Duck to help you debug those tricky prompts
Don't hold off any longer and apply now! If you have any questions, drop us a line at