We are looking for a highly skilled Lead AI Solutions Engineer to design, build, and optimize a Retrieval-Augmented Generation (RAG) system that underpins our self-serve analytics data applications. In this pivotal position, you will develop a scalable RAG platform, integrate multiple data sources, and create intuitive data interactions to empower teams across the organization.

As part of our RAG Initiative, you will collaborate with a cross-functional team to implement self-service AI-driven solutions - ranging from Natural Language Data Analysis and Data Discovery to other “analytics' assistant” we will be deploying to the business to streamlining data access, insights retrieval, and business process automation.

About A&I The Automation and Insights (A&I) department is at the forefront of transforming FDJ into a highly automated, data-driven powerhouse. In this dynamic environment, you'll work alongside experts in data, insights, and cutting-edge AI to build an AI-ready ecosystem that automates data management, insight generation, and machine-to-machine interactions. This isn't just about advancing technology; it's about reshaping our operational DNA to drive innovation, efficiency, and exceptional customer experiences in the new era of analytics and automation.

Key Responsibilities:

RAG System Development:

· Enhance, build new assistants and maintain existing scalable and modular RAG architectures for data retrieval and generation.

· Develop APIs and microservices to integrate RAG capabilities with existing data sources (not only user behaviour data, metadata and semantic layer, but also other sources e.g. HR systems, legal repositories, SharePoint, etc.).

· Manage and optimize LibreChat UI for chatbot interactions and Open WebUI Pipelines for backend model development.

· Strong experience working with large language models (e.g., GPT, Claude family and LLaMA) and embedding models (e.g., Sentence Transformers), including fine-tuning and performance optimization.

· Data Engineering & Integration:

· Build efficient data pipelines to support LLM-based querying, semantic search, and metadata retrieval.

· Maintain and troubleshoot Airflow pipelines for embedding extraction and document processing.

· Ensure data governance, security, and compliance across all applications.

· Manage Vector Database (PGVector, FAISS, etc.), including indexing and similarity search optimizations.

Security & Infrastructure Management:

· Collaborate with Platform Engineering teams to manage apps Kubernetes deployments on Kindred Cloud.

· Ensure security integrations with Azure SSO and SailPoint.

· Work with the Network & Security team to manage configurations for newly created services.

Testing & Deployment:

· Develop unit and integration tests to ensure system reliability and performance.

· Validate applications against real-world data and scenarios to assess LLM accuracy and output quality.

· Deploy applications in AWS Cloud environments, ensuring scalability and monitoring in production.

· Use Kubernetes, Docker, Helm and ArgoCD to manage deployments.

Documentation & Knowledge Transfer:

· Deliver technical documentation covering system architecture, APIs, and workflows.

· Conduct training sessions and presentations for internal teams to facilitate self-service capabilities and ongoing system enhancements.

Required Skills & Qualifications:

· 5+ years of experience in AI/ML engineering, data engineering or backend development.

· Strong knowledge of Python (LangChain, LangGraph and agent-based LLM worflows) and FastAPI with the focus on scalability and performance.

· Hands-on experience integrating with LLM providers such as OpenAI and Anthropic for both inference and evaluation workflows.

· Experience with LLM-based architectures, RAG, and NLP techniques.

· Hands-on experience using MLflow or similar tools to track model and prompt evaluation experiments.

· Proficiency in SQL, No-SQL, Redshift and data warehousing concepts.

· Experience integrating structured and unstructured data sources for AI-driven applications.

· Knowledge of dbt, metadata management, and semantic search.

· Cloud deployment experience in AWS or Kindred Cloud.

· Experience with Kubernetes, Terraform, and Helm for deployment management.

· Strong problem-solving skills and ability to work in a fast-paced, agile environment.

Ensure that you adhere to the Governance, Risk & Compliance (GRC) obligations for your role.

• Identify and raise any non-compliance incidents promptly to your line manager.
• Challenge processes, policies and projects that will negatively impact compliance within the Group.
• Complete all mandatory compliance training assigned to you.
• Reach out to the Compliance Teams if unsure of any of your compliance obligations or the requirements are unclear.