Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I'm a full-stack data engineer with 4+ years of experience in genomic big data analytics and cloud-native visualization app development. I excel at transforming complex interdisciplinary challenges into achievable engineering solutions, using AI (Agentic RAG) to optimize workflows. I enjoy building end-to-end data pipelines, scalable visualization tools, and research copilots that accelerate discovery. My work spans front-end visualization, back-end data processing, and cloud deployments, with a focus on reproducibility and impact.…I'm a full-stack data engineer with 4+ years of experience in genomic big data analytics and cloud-native visualization app development. I excel at transforming complex interdisciplinary challenges into achievable engineering solutions, using AI (Agentic RAG) to optimize workflows. I enjoy building end-to-end data pipelines, scalable visualization tools, and research copilots that accelerate discovery. My work spans front-end visualization, back-end data processing, and cloud deployments, with a focus on reproducibility and impact.

Li Yimin

Full Stack Developer, Data Scientist, AI Developer, +3





I'm a full-stack data engineer with 4+ years of experience in genomic big data analytics and cloud-native visualization app development. I excel at transforming complex interdisciplinary challenges into achievable engineering solutions, using AI (Agentic RAG) to optimize workflows. I enjoy building end-to-end data pipelines, scalable visualization tools, and research copilots that accelerate discovery. My work spans front-end visualization, back-end data processing, and cloud deployments, with a focus on reproducibility and impact.…I'm a full-stack data engineer with 4+ years of experience in genomic big data analytics and cloud-native visualization app development. I excel at transforming complex interdisciplinary challenges into achievable engineering solutions, using AI (Agentic RAG) to optimize workflows. I enjoy building end-to-end data pipelines, scalable visualization tools, and research copilots that accelerate discovery. My work spans front-end visualization, back-end data processing, and cloud deployments, with a focus on reproducibility and impact.

Available to hire

I’m a full-stack data engineer with 4+ years of experience in genomic big data analytics and cloud-native visualization app development. I excel at transforming complex interdisciplinary challenges into achievable engineering solutions, using AI (Agentic RAG) to optimize workflows.

I enjoy building end-to-end data pipelines, scalable visualization tools, and research copilots that accelerate discovery. My work spans front-end visualization, back-end data processing, and cloud deployments, with a focus on reproducibility and impact.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Intermediate

Language

English

Fluent

French

Intermediate

Work Experience

Full-Time Doctoral Researcher at Rega Institute, KU Leuven

December 1, 2021 - November 1, 2025

Led visualization app development and cloud deployment for interactive phylogeographic reconstructions: built a responsive React frontend to render geospatial layers and time-resolved diffusion; developed a Python ETL service to process large, heterogeneous inputs (>100k records, >1GB raster tiles) with normalization, caching, and compression that reduced payload by ~80%; containerized services with Docker and Kubernetes and automated deployments via CI/CD. Designed a cloud-native AWS backend with Terraform, API Gateway, Lambda, Amazon RDS (PostgreSQL) and Amazon S3 data lake for large assets. Performed large-scale Bayesian phylogenetic and phylogeographic analyses to study variant spread and integrated sequence metadata with environmental variables; parallelized MCMC runs on HPC clusters via SLURM and tuned calibration with temperature scaling in PyTorch. Engineered a hybrid AI-powered Research Copilot: ETL to ingest heterogeneous bioinformatics assets into a unified RAG knowledge bas