A leading FTSE 100 organisation is building out multiple AI teams focused on both AI product development and enterprise-wide AI transformation initiatives.
This is a production-first environment focused on deploying AI systems that are actively used, trusted, and continuously improved - not experimental proof-of-concepts.
Candidates should have proven experience building and deploying real-world LLM and agentic systems into production environments at scale.
Key Responsibilities
- Designing and building AI agents and agentic workflows powered by LLMs
- Developing multi-step intelligent systems incorporating reasoning, planning, memory, and tool orchestration
- Building and improving RAG pipelines and retrieval systems
- Working with MCP-style architectures / FastMCP / FastAPI
- Automating complex workflows and decision-making processes using AI
- Deploying scalable AI systems into production cloud environments
Required Experience
- Strong Python engineering skills with production-grade coding standards
- Proven experience shipping LLM-powered applications into production
- Hands-on experience with LangChain / LangGraph or similar frameworks
- Experience building AI agents with orchestration and tool usage
- Strong understanding of RAG architectures and LLM trade-offs
- Experience deploying systems across AWS, Azure, or GCP
- Strong product mindset with a bias toward delivery and impact
- SaaS or B2B AI product environments
- Evidence of AI systems actively delivering measurable business value
#J-18808-Ljbffr