Postdoc on cofolding models for In-Silico Drug Discovery

Johnson Johnson; Beerse; On-site; EUR 42,000 - 60,000; Full time

Job summary

Johnson & Johnson is recruiting a Postdoctoral Scholar in Beerse, Belgium for In Silico Drug Discovery. You will work on co-folding models, structure-based drug discovery, and AI/ML applications, joining a multidisciplinary team in Therapeutics Discovery.

The role focuses on data curation, training, benchmarking, and integration into discovery workflows, with opportunities for collaborations across CADD, biologics, and AI/ML groups.

Qualifications

• PhD in computational chemistry, structural bioinformatics, computational biology, or ML for biomolecular systems.
• Strong understanding of protein structure and structure-based modeling concepts.
• Experience with AI/ML model development, training, fine-tuning, and evaluation (e.g. PyTorch).
• Experience generating or working with structural datasets (protein–ligand, protein–protein, MD-derived data).
• Experience coding and developing research workflows in Python.
• Familiarity with HPC and GPU computing environments.
• Strong analytical, problem-solving, and scientific communication skills.
• Track record of scientific deliveries including peer-reviewed publications and presentations.
• Professional fluency in English.
• Up to 10% travel domestically and internationally.

Responsibilities

• Design, run, and analyze fine-tuning experiments for co-folding and structure-prediction models, benchmarking against baselines.
• Generate, curate, and manage training/validation datasets to support fine-tuning and evaluation.
• Assess model performance using structural and task-relevant metrics; contribute to evaluation best practices.
• Integrate fine-tuned co-folding models into end-to-end discovery workflows from inference to reporting.
• Collaborate with In Silico Discovery scientists across CADD, biologics, and AI/ML teams.
• Contribute to internal communication, documentation, and publication-ready summaries.

Skills

Python programming

AI/ML model development

PyTorch

Computational chemistry

Structural bioinformatics

English fluency

Education

PhD in computational chemistry or related field

Tools

HPC environments

GPU computing

Version control

Job description

At Johnson & Johnson, we believe health is everything. Our strength in healthcare innovation empowers us to build a world where complex diseases are prevented, treated, and cured, where treatments are smarter and less invasive, and solutions are personal. Through our expertise in Innovative Medicine and MedTech, we are uniquely positioned to innovate across the full spectrum of healthcare solutions today to deliver the breakthroughs of tomorrow, and profoundly impact health for humanity. Learn more at jnj.com .

As guided by Our Credo, Johnson & Johnson is responsible to our employees who work with us throughout the world. We provide an inclusive work environment where each person is considered as an individual. At Johnson & Johnson, we respect the diversity and dignity of our employees and recognize their merit.

Job Function:

Career Programs

Job Sub Function:

Post Doc - Drug Discovery & Pre-Clinical/Clinical Development

Job Category:

Career Program

All Job Posting Locations:

Beerse, Antwerp, Belgium

Job Description:

We are currently recruiting for a Postdoc on cofolding models for In-Silico Drug Discovery based in Beerse, Belgium.

At Johnson & Johnson, we believe health is everything. Our strength in healthcare innovation empowers us to build a world where complex diseases are prevented, treated, and cured, where treatments are smarter and less invasive, and solutions are personal. Through our expertise in Innovative Medicine and MedTech, we are uniquely positioned to innovate across the full spectrum of healthcare solutions today to deliver the breakthroughs of tomorrow, and profoundly impact health for humanity.

We are seeking a Postdoctoral Scholar to join our cutting‑edge In Silico Discovery department within Therapeutics Discovery at J&J. This position is intended for early‑career scientists with strong technical training and research interest in co‑folding models, structural bioinformatics, and AI/ML for drug discovery.

The position focuses on research and development of fine‑tuning strategies for co‑folding models applied to structure‑based drug discovery. The role will involve generating and curating training and benchmarking datasets, evaluating task‑specific performance, and integrating fine‑tuned models into discovery workflows. The Postdoctoral Scholar will work closely with computational scientists in a collaborative, multidisciplinary research environment.

• Design, run, and analyze fine‑tuning experiments for co‑folding and structure‑prediction models, including benchmarking against internal and external baselines.
• Generate, curate, and manage training and validation datasets (e.g. complex structures, MD‑derived conformational ensembles, and project‑specific data) to support model fine‑tuning and evaluation
• Assess model performance using appropriate structural and task‑relevant metrics and contribute to best practices for model evaluation
• Integrate fine‑tuned co‑folding models into end‑to‑end discovery workflows, including inference, reporting, and documentation
• Collaborate closely with In Silico Discovery scientists across CADD, biologics, and AI/ML teams to align research outputs with drug‑discovery needs
• Contribute to internal scientific communication, documentation, and publication‑ready summaries of research outcomes
• Participate in external collaborations and consortia related to co‑folding and structural biology AI, supporting integration of research deliverables
• Engage in professional development through training courses, conferences, and internal scientific meetings as aligned with project milestones

Required:

• PhD in computational chemistry, structural bioinformatics, computational biology, or machine learning applied to biomolecular systems.
• Strong understanding of protein structure and structure‑based modeling concepts.
• Experience with AI/ML model development, training, fine‑tuning, and evaluation (e.g. PyTorch or similar frameworks).
• Experience generating or working with structural datasets (e.g. protein‑ligand or protein‑protein complexes, MD‑derived data).
• Experience coding and developing research workflows in Python
• Familiarity with HPC and GPU computing environments.
• Strong analytical, problem‑solving, and scientific communication skills.
• Track record of scientific deliveries, including peer reviewed first‑author publications and presentations at major national meetings is required.
• Professional fluency in English.
• Up to 10% travel both domestically and internationally is required.

Preferred skills:

• Postdoctoral or doctoral research exposure to co‑folding models, structural AI, or related foundation models.
• Experience benchmarking ML models for scientific or drug‑discovery applications
• Familiarity with protein‑ligand or antibody‑antigen modeling, docking, and virtual screening concepts.
• Experience with reproducible research practices (version control, testing, documentation).
• Exposure to drug‑