Key skills
CloudDockerPostgresPythonAIRAGLangChainLlamaIndexAgenticFastAPI
About this role
Role Overview
- Architect and optimize AI-driven systems, ensuring scalability and performance.
- Implement vector/graph database solutions and RAG techniques for information storage and retrieval.
- Develop agentic reasoning workflows using frameworks like LangChain or LlamaIndex.
- Lead the full AI lifecycle: data ingestion, embedding, extraction, synthesis, prompt engineering, and workflow orchestration.
- Deploy, monitor, and maintain models in Docker-based, containerized environments.
- Collaborate with cross-functional teams to align AI capabilities with business goals.
- Contribute to internal knowledge sharing and mentor junior engineers.
Requirements
- Proven expertise in utilizing Python-based frameworks such as FastAPI for API development, Celery for task management, and Postgres for database solutions.
- Experience with vector and graph databases, and RAG-based architectures.
- Experience of with agentic frameworks and orchestration frameworks such as LangChain or LlamaIndex.
- Solid understanding of LLMs, embeddings, and prompt engineering.
- Experience designing multi-agent systems or autonomous workflows.
- Hands-on experience with Docker and deploying containerised, cloud-native tools.
- Experience with advanced retrieval-augmented generation techniques, including:
- TAG (Tool-Augmented Generation) – integrating external tools to enhance generation capabilities.
- CAG (Context-Aware Generation) – leveraging dynamic context to improve relevance and coherence.
- GraphRAG (Graph-Augmented Retrieval-Augmented Generation) – utilizing graph-based structures to enrich retrieval and reasoning.
Tech Stack
- Cloud
- Docker
- Postgres
- Python
Benefits
- hybrid working
- competitive base salary
- non-contributory pension
- discretionary bonus
- insurances including health (family) and dental cover
- many other benefits to enhance financial, physical, social and psychological health