Take retrieval and ranking models from notebook to production for our enterprise search product.
About the role
Our search product handles millions of documents across regulated industries.
You will work with applied researchers to productionise models, own the serving stack and drive measurable quality improvements.
What you will do
- Build and evaluate retrieval and ranking pipelines
- Own model serving infrastructure and latency budgets
- Design offline and online evaluation harnesses
What we are looking for
- 3+ years in applied ML with production ownership
- Strong Python and PyTorch experience
- Experience with vector search or information retrieval
Perks and benefits
- Conference budget
- Top-tier hardware
- Relocation support
Skills
246 views