AI Engineer

AI Engineer — GenAI / LLM Applications

We are engaging a Senior AI Engineer to build and scale GenAI-powered features as part of a data & AI delivery programme for a global, strategy-led technology consultancy.

This is a production-focused engineering role, working at the intersection of LLM integration, Python services, and enterprise data platforms, with Palantir Foundry as the core environment

What you'll be doing

• Building and iterating LLM-powered application features (e.g. copilots, summarisation, workflow augmentation)
• Integrating LLMs into backend services and business workflows (API-driven)
• Translating structured enterprise data into usable LLM context
• Deploying and testing AI features within Foundry / AIP environments
• Working closely with data engineers to ensure data is fit for AI consumption
• Monitoring and improving output quality, reliability, and performance

What we're looking for

Must-have

• Proven experience delivering GenAI / LLM-powered applications in production
• Strong Python engineering (APIs, services, clean modular code)
• Experience integrating LLMs into real systems (not just prototypes or notebooks)
• Solid understanding of:
  • prompt design and iteration
  • LLM limitations (hallucination, context handling)
  • structured input/output handling

Nice-to-have 

• Exposure to frameworks like LangChain or similar orchestration tools
• Experience working with enterprise data platforms such as Palantir Foundry or Databricks
• Familiarity with RAG patterns (even if not building full custom pipelines)
• Experience with observability / tracing of LLM interaction

If you are experienced in turning LLM capability into reliable product feature - not just experiments, we want to hear from you.