Incoming PhD Student (October 2026)

Jaronchai Dilokkalayakul

Data engineer and bioinformatics researcher, focusing on heterogeneous data integration.

Tohoku University, Sendai. From Bangkok, previously data engineer at IBM.

Current focus

Making biological monitoring data interoperable.

I work on bioinformatics, data platforms, and scientific workflow design. The aim is to connect scattered biological data and make evidence easier to reason with.

AI and LLM

Large Language Models, multimodal models, RAG.

Data Infrastructure

Batch, streaming, storage, monitoring.

Science Communication

Talks, presentation, posters.

Peripherals: coffee, productivity tools, note taking, and stationery.

Research

Publications

  1. Master's thesis

    Awaiting publication

    Provenance-Preserving Framework for Integrating Heterogeneous Ecosystem Monitoring Data with Large Language Models

    Tohoku University

    Citation, links, and PDF will be added once the thesis is public.

Upcoming events

Where I will be next

  1. DITTO Summit 2026

    Workpia Yokohama, Japan

    Digital Twins of the Ocean summit; next stop for ocean data, interoperability, and monitoring systems.

Conference record

Recent talks

All talks
  1. Provenance-Preserving Large Language Model Question-Answering System for Heterogeneous Biodiversity Monitoring Data
    The 20th International Biotechnology Symposium and Exhibition · Kobe, Japan
    Slides Abstract Poster
  2. Provenance-Preserving Framework for Integrating Heterogeneous Ecosystem Monitoring Data with Large Language Models
    Earth, Sea and Sky XII: Workshop for International Joint Graduate Program & Core Research Cluster in Earth and Environmental Sciences · Tohoku University, Sendai, Japan
    Abstract Poster
  3. Data Integration and Platform Unification Challenges in Marine Bioinformatics
    COSMEC and ANEMONE Global Joint Symposium 2026 · Tokyo, Japan
    Slides Video
  4. The 11th EAFES International Congress - Context-Aware Marine Plankton Classification with Multimodal Large Language Model and Retrieval-Augmented Generation Reasoning
    The 11th EAFES International Congress · Tokyo, Japan
    Abstract Poster
  5. IMBC2025 Oral Presentation Awards - Automated Taxonomic Identification of Marine Plankton
    International Marine Biotechnology Congress 2025 · Brest, France
    Slides Abstract Award

Selected works

Projects and research notes

All writing
  1. Data Platform: Batch + Streaming + Lakehouse + Monitoring for Bioinformatics
  2. IMBC2025 Presentation Slides PDF Companion
  3. Talking about Planktons: First International Conference in Hawaii
  4. Advancing Plankton Monitoring: LLM with RAG Approach
  5. How to LLM+RAG with Milvus VectorDB WALKTHROUGH