ETH Zurich Postdoctoral Researcher in Multimodal Reasoning Models for Oncology (2026)
Position Description
ETH Zurich is seeking an exceptional and highly motivated Postdoctoral Researcher to lead research on multimodal reasoning models for oncology. The project focuses on developing, post-training, and evaluating flexible AI models that can support complex oncologic diagnostic and therapeutic decision-making in a safe, transparent, and clinically grounded manner.
The successful candidate will work on oncology-focused multimodal reasoning models that combine language, vision, biomedical knowledge, clinical context, and relevant patient-level data to produce reliable, auditable, and uncertainty-aware outputs. A major focus is the development of AI-based reasoning strategies for oncology, including tool-augmented inference, multi-agent workflows, process supervision, verifier-guided training, and reinforcement learning-based post-training.
This position is embedded within a highly interdisciplinary collaboration between ETH Zurich, Kaiko.ai, and clinical partners, offering an opportunity to advance foundational AI research while working toward real-world translation in oncology. The position is located at ETH Zurich's Department of Biosystems Science and Engineering (D-BSSE) in Basel, Switzerland.
Position Location
The position is based at ETH Zurich, Department of Biosystems Science and Engineering (D-BSSE) in Basel, Switzerland. The successful candidate will work at the intersection of AI research and clinical oncology, with close collaboration with Kaiko.ai and clinical partners.
Application Deadline
Applications are being collected for 1 month until July 19, 2026, with the option to extend this window.
Application Deadline: July 19, 2026 (initial collection window)
Position Type: Full-time, fixed-term
Recommendation: Submit your application as early as possible. Applications via email, social media, or postal services will not be considered.
Host Institution
ETH Zurich – one of the world's leading universities specialising in science and technology. The Department of Biosystems Science and Engineering (D-BSSE) is located in Basel, Switzerland, at the heart of the country's life sciences hub. The research group is actively engaged with the ETH AI Center and the SwissAI initiative, providing access to a vibrant and world-class AI community.
Level and Fields of Study
Level: Postdoctoral Researcher.
Fields: Machine Learning, Artificial Intelligence, Medical AI, Biomedical Informatics, Computational Biology, Oncology, Clinical Decision-Making, Multimodal Reasoning.
Key research areas include:
- Reasoning Models for Oncology: Multimodal language model architectures, integration of clinical context, biomedical literature, and patient-level multimodal evidence.
- Reasoning Strategies, Agents, and Tool Use: Retrieval from literature and clinical guidelines, clinical trial matching, multi-agent systems, and citation-grounded outputs.
- Process Supervision and Post-Training: Reinforcement learning, process-level supervision, calibration, and safety-aware optimization.
- Clinical Evaluation and Safety: Guideline concordance, diagnostic reasoning quality, tool-use reliability, and clinician-in-the-loop evaluation.
Target Group
Highly qualified researchers with a PhD in Computer Science, Machine Learning, Medical AI, Biomedical Informatics, Computational Biology, or a related field. The position is open to candidates from all nationalities with a strong publication record in AI/ML, medical AI, or related areas.
Position Duration & Benefits
Duration: Full-time postdoctoral position (fixed-term).
Compensation: Competitive salary according to ETH Zurich standards, with excellent research infrastructure.
Benefits include:
- Access to unique multimodal clinical datasets
- Collaboration with Kaiko.ai and clinical partners
- Access to the Alps cluster with 10,000 high-end GPUs within SwissAI projects
- Highly interdisciplinary environment spanning AI, oncology, and clinical informatics
- Membership in the ETH AI Center and SwissAI community
- World-class research infrastructure and facilities
📊 Summary of Position:
Salary: Competitive (ETH Zurich standards)
Duration: Full-time, fixed-term
Access: Alps cluster (10,000 GPUs) + ETH AI Center + SwissAI
Eligibility & Qualifications
Required qualifications:
- PhD in Computer Science, Machine Learning, Medical AI, Biomedical Informatics, Computational Biology, or a related field.
- Strong programming skills in Python and modern ML frameworks.
- Experience with deep learning and large language models.
- Strong publication record in AI/ML, medical AI, computational biology, biomedical informatics, or related areas.
- Ability to work in highly interdisciplinary research environments.
Preferred qualifications:
- Experience with foundation models, multimodal models, or biomedical/clinical language models.
- Experience with reasoning models, agents, tool use, or compound LLM systems.
- Experience with LLM post-training methods such as RLHF, RLAIF, verifier-guided training, or process supervision.
- Familiarity with retrieval methods for LLMs (dense/sparse retrieval, agentic retrieval, or hybrid approaches).
- Experience with medical AI applications (oncology, genomics, imaging, or clinical NLP).
- Experience with scalable ML infrastructure, multi-node GPU training, or local/private deployment settings.
✅ Eligible Candidates
- PhD in Computer Science, ML, Medical AI, or related field.
- Strong Python and ML framework skills.
- Experience with deep learning and LLMs.
- Strong publication record.
- Ability to work in interdisciplinary environments.
❌ Ineligible Candidates
- No PhD in a relevant field.
- Insufficient programming or ML skills.
- No experience with deep learning or LLMs.
- Weak publication record.
- Unable to work in interdisciplinary settings.
Application Procedure
- Prepare required documents – Concatenate the following into one PDF:
- CV – including a list of most significant publications
- Bachelor and Master transcripts
- Motivation letter – explaining motivation and fit to the project and the host lab
- Letters of recommendation – if available, or a list of names that can be queried for letters of recommendation
- Submit online application – Applications must be submitted exclusively through the ETH Zurich online application portal. Applications via email, social media, or postal services will not be considered.
- Application deadline – Submit by July 19, 2026 (1-month collection window, with option to extend).
- Review process – Applications are reviewed on a rolling basis. Shortlisted candidates are contacted for interviews.
- Offer – The successful candidate receives a formal offer from ETH Zurich.
Important notes: Questions regarding the position should be directed to [email protected] (no applications). Only applications submitted through the online portal will be considered.
Official Website & Application Link
ETH Zurich – Postdoctoral Researcher in Multimodal Reasoning Models for Oncology
Research Group Website: Available via the ETH Zurich D-BSSE website
Questions: [email protected] (no applications)
💡 Final Thoughts and Key Requirements
This postdoctoral position at ETH Zurich offers a unique opportunity to work at the intersection of artificial intelligence and oncology, developing foundational models that can transform cancer diagnosis and treatment. With access to unique clinical datasets, cutting-edge GPU infrastructure (the Alps cluster with 10,000 GPUs), and a world-class research community, successful candidates can make significant contributions to both AI research and clinical practice.
Key strategies for a successful application:
- Ensure your PhD is in a relevant field (Computer Science, ML, Medical AI, Biomedical Informatics, or Computational Biology).
- Highlight experience with large language models, foundation models, or multimodal AI.
- Emphasize any previous work on reasoning models, agents, tool use, or compound LLM systems.
- Showcase experience with post-training methods such as RLHF, RLAIF, or process supervision.
- Demonstrate familiarity with retrieval methods for LLMs (dense retrieval, agentic retrieval, or hybrid approaches).
- Mention any experience with medical AI applications, particularly oncology, genomics, or clinical NLP.
- Prepare a compelling motivation letter that explains your fit to the project and the host lab.
- Submit your application by July 19, 2026 through the ETH Zurich online portal.
Important reminders: Applications via email, social media, or postal services will not be considered. Questions should be directed to [email protected] (no applications). The position is based in Basel, Switzerland, offering an excellent quality of life and proximity to Europe's leading life sciences hub.
ETH Zurich Postdoctoral Researcher – Multimodal AI Oncology 2026 – FAQ
What is the position about?
This is a postdoctoral researcher position at ETH Zurich focusing on developing multimodal reasoning models for oncology, combining AI, machine learning, and clinical decision-making for cancer care.
What qualifications are required?
A PhD in Computer Science, Machine Learning, Medical AI, Biomedical Informatics, or a related field, with strong programming skills in Python, experience with deep learning and LLMs, and a strong publication record.
What is the application deadline?
The initial application collection window closes on July 19, 2026.
Where is the position located?
The position is based at ETH Zurich's Department of Biosystems Science and Engineering (D-BSSE) in Basel, Switzerland.
What research topics will I work on?
Topics include reasoning models for oncology, multimodal language models, tool-augmented inference, multi-agent systems, process supervision, reinforcement learning, and clinical evaluation of AI systems.
How do I apply?
Submit your application through the ETH Zurich online application portal. Applications via email, social media, or postal services will not be considered.
What resources are available?
Access to the Alps cluster with 10,000 high-end GPUs, unique multimodal clinical datasets, collaboration with Kaiko.ai and clinical partners, and membership in the ETH AI Center and SwissAI community.