Data Scientist–Agentic Bioinformatics

Vlaams Instituut voor Biotechnologie (VIB); Vlaams-Brabant; Remote; EUR 70,000 - 100,000; Full time

Benefits offered by this job

Salary in line with VIB scales

Flexible working hours

International research environment

Training and mentoring

Job summary

Vlaams Instituut voor Biotechnologie (VIB) – Leuven/CCB is seeking a Data Scientist with a bioinformatics background to explore, build, and deploy tools based on large language models that support cancer biology research. You will work on agentic workflows to help researchers find methods, write analyses, and handle multi-omics data.

You will join a growing team led by Dr. Masoomeh Rahimpour, collaborate with the Integrative Cancer Genomics lab and the ML Unit of VIB.AI, and contribute to

Qualifications

• PhD or equivalent experience in bioinformatics/computational biology.
• Strong Python programming skills.
• Hands-on experience with LLMs via APIs or open-weight models.
• Working knowledge of common bioinformatic workflows (sequencing, single-cell, spatial).
• Ability to explain AI concepts to non-specialists.

Responsibilities

• Build LLM-based tools and agentic workflows for bioinformatics tasks.
• Connect LLM tools to pipelines, HPC, and databases.
• Evaluate reliability, correctness, and data privacy of AI tools.
• Deploy and maintain tools in collaboration with ML Unit and HPC centers.
• Stay up to date with LLMs and AI methods and share best practices.

Skills

Python

LLMs

Bioinformatics

Data analysis

English communication

Education

PhD in Bioinformatics/ Computational Biology

Tools

LangGraph

Open models

HPC

Job description

Bioinformatics & AI Expertise Unit

VIB–KU Leuven Center for Cancer Biology (CCB), Leuven, Belgium

The VIB–KU Leuven Center for Cancer Biology (CCB) is a leading research institute focused on understanding cancer biology and developing innovative therapies. Our Bioinformatics & AI Expertise Unit provides advanced computational support to multiple research groups within CCB (Learn more: Bioinformatics & AI).

We are seeking an Data Scientist with a background in bioinformatics or computational biology to explore, build, and deploy tools based on large language models (LLMs) that support research at CCB. This includes agentic workflows that help researchers find suitable methods, write and run analysis code, and work with multi‑omics and spatial data. You will critically evaluate these tools, bring the useful ones into daily use across research groups, and help the CCB community use them effectively and responsibly.

You will join a growing team led by Dr. Masoomeh Rahimpour and work closely with the Integrative Cancer Genomics lab of Prof. Jonas Demeulemeester, other CCB Expertise Units, and the ML Unit of VIB.AI, the VIB Center for AI & Computational Biology (Learn more: VIB.AI).

Key Responsibilities

• Build LLM-based tools and agentic workflows for bioinformatics tasks, such as assistants that help run and document standard analyses, retrieval over internal protocols and documentation.
• Connect LLM tools to existing bioinformatics resources, including our pipelines, HPC environment, databases, and public resources (e.g., via tool calling or MCP).
• Evaluate the reliability of these tools on realistic research tasks, with attention to correctness, reproducibility, and data privacy.
• Deploy and maintain tools for CCB researchers in collaboration with the ML Unit at VIB.AI and the Vlaams Supercomputer Centrum (VSC).
• Stay up to date with state‑of‑the‑art methods in LLMs, AI agents, and computational biology; evaluate, benchmark, and introduce relevant tools and best practices.
• Deliver training and workshops on the practical and responsible use of LLMs and AI tools in research.

Profile

We welcome applications from all backgrounds and career paths. If this role interests you and you meet most of the essential requirements, we encourage you to apply.

• A PhD in Bioinformatics, Computational Biology, Computer Science, or a related field or equivalent professional experience (e.g. in industry).
• Strong programming skills in Python.
• Hands‑on experience with LLMs (via APIs or open‑weight models), for example prompt design, or tool/function calling.
• Working knowledge of common bioinformatic workflows (e.g. sequencing, single‑cell, or spatial data), enough to judge whether an AI‑generated analysis makes sense.
• Ability to explain AI concepts and their limitations clearly to non‑specialists.
• Willingness to keep learning and to share knowledge with colleagues.
• Good communication skills in English.

Nice to have:

• Experience with retrieval‑augmented generation (RAG) over scientific literature or internal documentation.
• Experience with agent frameworks (e.g. LangGraph or similar).
• Experience running open‑weight models on local or HPC hardware.

What We Offer

• Access to unique datasets and cutting‑edge infrastructure.
• A collaborative and international research environment.
• Support for your personal and professional development through training, mentoring, and career development.
• A salary in line with VIB salary scales, based on your experience, and a benefit package.
• A full‑time, indefinite contract with flexible working hours.