.png){kind=logo}
Arwen Yang
Staff Applied Scientist specializing in multimodal LLM safety, robustness, and retrieval
Connect with Arwen
Arwen already has a relationship with Reval, so a warm intro from us gets a much better response than cold outreach.
Recommended
Already have an account?
About
Built a production LLM-driven archival assistant that turns large, low-quality scanned handwritten files (120+ pages) into structured datasets, overcoming context-window and hierarchy challenges with a two-phase LLM + rules pipeline and reaching 98.1% accuracy (Gemini-2.5 Flash). Also orchestrated a large human-in-the-loop effort with 78 archivists, producing 2,400 high-quality annotations in 4 days via detailed rubrics and support.
Experience
Education
Key Strengths
- Built and deployed LLM-based archival system converting handwritten unstructured files into structured outputs (JSON/CSV/XLSX)
- Solved long-document context/hierarchy issues via two-phase pipeline (LLM extraction + rule-based hierarchy processing)
- Achieved 98.1% accuracy using Gemini-2.5 Flash
- Designed quality controls for low-quality scans (image enhancement + confidence-based flagging for manual review)
- Strong model selection/evaluation approach (benchmarks/leaderboards, small-model + toy dataset prototyping to control cost)
- Effective cross-functional collaboration with non-technical stakeholders (guided 78 archivists; collected 2400 high-quality annotations in 4 days)
Discover more candidates like Arwen
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent