Role Overview
An AI Engineer (Spatial Intelligence) at a global technology company's Edinburgh research centre, building next-generation maps powered by edge AI. The role adapts multimodal foundation models, geospatial data and on-device inference to develop spatial intelligence capabilities.
Responsibilities
- Fine-tune, compress and deploy multimodal foundation models (LLMs and VLMs) for consumer-grade edge hardware
- Design pipelines turning geospatial data into structured, LLM-ready representations for spatial reasoning
- Architect high-performance vector search and embedding-based retrieval over distributed spatial data
- Build data pipelines adding real-time semantic context to mapping systems (thematic mapping)
- Develop agent-based workflows combining models, retrieval and spatial tools into end-to-end systems
- Build proof-of-concept demonstrators testing new model capabilities
- Evaluate model accuracy, latency and memory trade-offs on device
Requirements
- PhD in Computer Science, Robotics, Engineering or related technical field
- At least 2 years' experience fine-tuning or building on LLMs, foundation models or multimodal architectures such as vision-language models
- Practical experience with geospatial data and/or vector embeddings and semantic search, including RAG
- Strong Python skills, including multi-step LLM or agent pipelines with orchestration frameworks such as LangGraph, AutoGen or Pydantic AI
- Prototyping mindset: able to take an idea to a working demo quickly