We're looking for a senior AI engineer to build and stabilise ) applications for employees and customers, from retrieval to answer generation.
What you'll do
- Implement ingestion pipelines with chunking, embeddings and incremental refresh.
- Apply security trimming, ACL propagation, prompt templates and agent guardrails.
- Set up evaluation and tracing with on .
- Deploy services using and .
- Monitor latency, token consumption, run costs and quality regressions.
- Support hypercare through incident analysis, tuning, runbooks and handover.
What you bring
- Senior-level and experience with large language models (LLMs).
- OpenAI Service, Azure AI Search and vector databases.
- ), Terraform and Azure DevOps pipelines.
- or , native.
- , C1.
What's next?
The people who do well here are the ones who saw themselves in this description. Not because they match every line, but because the mission felt right for them.
We are actively hiring for this position. Applications are reviewed by our team, and matching profiles receive a call to discuss the role in detail.
It takes under a minute to apply. Your email, your CV. That is all we need to start the conversation.