The opportunity
Develop the model-facing layer behind useful AI products. You will work on retrieval, prompts, structured outputs and evaluation, with attention to what happens when a model is uncertain or a dependency fails.
This role connects experimentation with production engineering. Bring a testing mindset, a habit of measuring quality and the ability to make model behaviour understandable to the rest of the team.
What you’ll do
- Build LLM features using well-defined inputs and structured outputs
- Implement and improve retrieval pipelines and grounding
- Create representative evaluation datasets and regression checks
- Measure answer quality, latency and inference cost
- Implement fallbacks, retries and safe handling of untrusted content
- Collaborate with backend and product engineers on release quality
What you’ll bring
- Strong Python or TypeScript development skills
- Hands-on experience building LLM applications
- Understanding of embeddings, retrieval and prompt design
- Ability to evaluate quality beyond individual successful examples
- Experience with APIs, version control and automated testing
Nice to have
- Experience comparing model providers
- Familiarity with reranking and vector search
- Experience with inference optimisation
Your toolkit
Make your next move.
Share your CV, portfolio or relevant project links through the application form. Include the role title and job reference in your response.
Salary and role-specific working arrangements will be discussed during hiring.
Apply for LLM Engineer. Include the job reference ADZ-002 in your response.
Open application form ↗Applications are handled separately from this public job board. Privacy policy.
