.png){kind=logo}
Min-Han Shih
Junior Machine Learning Engineer specializing in speech and multimodal AI
Connect with Min-Han
Min-Han 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
New grad who has shipped a production vision-language recommendation feature for a pet camera/mobile app, including building a tagged video dataset with human annotators and optimizing inference by FPS downsampling under device compute limits. Also built a multimodal MLLM benchmark using an LLM-as-judge (GPT-5-thinking) with a feedback loop, validated against human scoring, and measured post-feedback quality gains (12% average score improvement).
Experience
Education
Key Strengths
- Deployed production VLM feature for pet daily highlight recommendations
- Solved on-device inference constraints by validating FPS downsampling with minimal quality impact
- Designed evaluation experiment across multiple FPS settings (15/10/8/5/3/1) to choose best tradeoff
- Built multimodal benchmark using LLM-as-judge plus feedback loop; improved average judged score by 12%
- Validated LLM-judge scoring alignment with human raters
- Iterated with beta-user feedback and shipped feature that increased user engagement (Q1)
Discover more candidates like Min-Han
Search across thousands of pre-screened, high-quality, high-intent candidates on Reval.
Search Talent