.png){kind=logo}
Hsi-Chun Wang
Mid-level Data Scientist specializing in LLM development and scalable ML pipelines
Connect with Hsi-Chun
Hsi-Chun 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 production LLM pipelines for evidence-based scoring in two domains: biomedical literature mining (scoring ~2700 drug compounds vs gene targets/mechanisms) and long-horizon news analytics (35 years of Chinese articles). Emphasizes reliability at scale (retries/checkpointing/validation), rigorous empirical model benchmarking (GPT-4o/mini/5), and translating results into stakeholder-friendly visual narratives.
Experience
Education
Key Strengths
- Built and productionized an LLM literature-mining system scoring ~2700 drug compounds against biological targets/mechanisms
- Designed reliable large-scale pipelines with retries, checkpointing, logging, and partial re-runs to handle API instability
- Improved scoring integrity by separating 'no evidence' vs unrelated vs negative evidence via prompt constraints and post-processing rules
- Strong empirical model selection approach (GPT-4o vs GPT-4o-mini vs GPT-5) using correlation metrics and scatter plots
- Modular workflow design with strict I/O schemas and practical subset-to-full-scale validation
- Effective communication of LLM results to non-technical stakeholders using visualizations and concrete examples (35-year Chinese news trend analysis)
Discover more candidates like Hsi-Chun
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent