Exa
Research, Evals
$180K–$350K
San Francisco, California · On-site · Full-time · Posted Oct 15, 2025
- Visa sponsorship
- Open to sponsoring international candidates, including STEM OPT, OPT, H1B, O1, and E3; sponsorship is not guaranteed.
About the job
Design and build evaluation frameworks and scalable pipelines that measure search quality and guide Exa’s search-model research.
What you'll do
- Design and implement evaluation frameworks and suites for search.
- Build scalable evaluation pipelines to track regressions, drift, and quality across billions of documents.
- Create datasets and benchmarks, and partner with research, engineering, and product teams to improve search models.
What they ask for
- Hands-on ML experience in training, fine-tuning, or evaluating models.
- Strong engineering fundamentals and ability to build reliable systems.
- Enjoy working with data, building evaluation sets, inspecting edge cases, and designing measurement strategies.
Nice to have
- Experience related to embeddings or LLMs.
Pay
$180K – $350K (base salary)
Tools
Python, Rust
AI focus
Evaluate search engines in an LLM world and build evaluation systems that inform improvements to search models.
Model-written summary · the original posting is authoritative