.png){kind=logo}
Fangjian Xiong
Junior Machine Learning Engineer specializing in NLP and biomedical entity extraction
Connect with Fangjian
Fangjian 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 and deployed a production LLM-powered biomedical knowledge extraction pipeline that processed millions of papers to identify tools/techniques and produce a unified knowledge graph via active learning NER (Prodigy + spaCy transformers) and entity linking (Bio-tools/Wikidata). Addressed hard NLP engineering challenges like WordPiece span-offset alignment and scaled inference over ~1.5M documents using batching/caching, containerized services, async workers, and orchestration with Prefect/Airflow.
Experience
Education
Key Strengths
- Built and deployed end-to-end LLM-powered biomedical knowledge extraction system to production
- Scaled NLP/LLM inference across ~1.5M documents while controlling GPU costs
- Solved token-offset alignment and entity-collision issues in dense scientific text (WordPiece/span labeling)
- Designed robust multi-stage pipelines with orchestration (Prefect/Airflow), retries, caching, and parallelism
- Strong evaluation and reliability practices (unit tests, offline benchmarks, shadow deployments, monitoring)
- Effective collaboration with non-technical researchers; translates domain needs into technical requirements and trade-offs
Discover more candidates like Fangjian
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent