.png){kind=logo}
Jacqueline Zhang
Mid-level Machine Learning Engineer specializing in LLMs, fairness, and healthcare ML
Connect with Jacqueline
Jacqueline 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 a master’s thesis focused on domain-adaptive knowledge distillation for LLMs (LLaMA2/sheared LLaMA), showing improved perplexity and ROUGE-L on biomedical data. Also built real-world data linking and search systems: integrated ClinicalTrials.gov with FAERS using fuzzy matching + embeddings, and delivered an LLM-powered FAQ recommender at Hyperledger using sentence-transformers, FAISS, and fine-tuning to mitigate embedding drift.
Experience
Education
Key Strengths
- Built domain-adaptive knowledge distillation pipeline for LLMs using Hugging Face/PyTorch/FSDP
- Demonstrated measurable NLP improvements (reduced domain perplexity, improved ROUGE-L)
- Designed multi-stage entity resolution workflow across ClinicalTrials.gov and FAERS using fuzzy matching + spaCy
- Validation strategy combining string similarity, embedding comparison, and targeted manual review with tiered confidence bands
- Built LLM-powered FAQ recommendation system using sentence-transformer embeddings + FAISS similarity search
- Addressed embedding drift by fine-tuning on curated QA pairs
- Production-minded data engineering practices: modular stages, testability, and automated validation checks with logging
Discover more candidates like Jacqueline
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent