.png){kind=logo}
Rebecca Witmer
Principal Data Scientist specializing in NLP and Generative AI
Connect with Rebecca
Rebecca 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
ML/NLP practitioner with experience building an embedding-based ad matching and search system at Vericast (BERT embeddings + similarity search) to replace a third-party taxonomy approach, evaluated via a human-curated gold standard. Also built a custom NER pipeline at Allstate for auto accident claims calls using a bidirectional LSTM and achieved 90%+ F1, with a strong emphasis on production-grade ML workflows (testing, CI/CD, orchestration, versioning, validation).
Experience
Education
Key Strengths
- Built embedding-based ad-to-content matching system replacing rigid taxonomy classification
- Designed evaluation using human-curated gold standard and top-10 recommendation accuracy comparisons
- Applied NER on auto accident claims call data with custom entity schema and human-labeled training set
- Established clear model quality gates for production (e.g., 90%+ F1) and achieved target
- Production-minded ML workflow practices: testing, CI/CD, modularization, logging/error handling, orchestration, model versioning, data validation
Discover more candidates like Rebecca
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent