We are 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 of the position is the development of AI-based reasoning strategies for oncology, including tool-augmented inference, multi-agent or compound model workflows, process supervision, verifier-guided training, and reinforcement learning-based post-training. The goal is to build systems that can justify recommendations, cite supporting evidence, calibrate uncertainty, defer appropriately, and operate safely in clinically realistic settings.

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.

Reasoning Models for Oncology 

Development and adaptation of oncology-focused foundation models capable of reasoning over complex clinical questions, including diagnosis, molecular interpretation, treatment selection, and longitudinal care.

This may include:

• Multimodal language model architectures
• Integration of clinical context, biomedical literature, guidelines, and patient-level multimodal evidence
• Adaptation and evaluation on public and institutional oncology datasets
• Development of uncertainty-aware and safety-aware reasoning behavior

Reasoning Strategies, Agents, and Tool Use

Development of model workflows that can use external tools and knowledge sources in a reliable and auditable way.

Examples include:

• Retrieval from literature, clinical guidelines, and trial databases
• Clinical trial matching and therapy evidence lookup
• Variant interpretation and molecular knowledgebase use
• Multi-agent systems for decomposing complex oncology tasks into hierarchical context streams
• Citation-grounded and traceable outputs suitable for expert review

Process Supervision and Post-Training

Development of post-training methods that improve clinical reasoning quality, reliability, and safety.

This may include:

• Process-level supervision for intermediate reasoning steps
• Outcome-based supervision using expert or guideline-derived signals
• Reinforcement learning for oncology-specific reasoning behavior
• Comparison and development of RL training approaches
• Calibration, abstention, and safety-aware optimization

Clinical Evaluation and Safety

Evaluation of oncology reasoning models in clinically meaningful settings.

Key evaluation dimensions include:

• Guideline concordance
• Diagnostic and therapeutic reasoning quality
• Molecular interpretation accuracy
• Tool-use reliability
• Citation quality and evidence grounding
• Calibration, uncertainty, and appropriate deferral
• Trace auditability and clinician-in-the-loop evaluation

Must Have

• 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

• 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, including dense/sparse retrieval, agentic retrieval, or hybrid approaches
• Experience with medical AI applications, particularly oncology, genomics, imaging, or clinical NLP is a plus, but not required
• Experience with scalable ML infrastructure, multi-node GPU training, or local/private deployment settings

• A full-time postdoctoral position at ETH Zurich, one of the world’s leading research universities
• This project is a collaboration between our lab at ETH Zurich (D-BSSE located in Basel) and Kaiko.ai
• Opportunity to work on cutting-edge foundation models for real-world oncology reasoning
• Access to unique multimodal clinical datasets and close collaboration with Kaiko.ai and clinical partners
• Highly interdisciplinary environment spanning AI (foundation models, MLLMs, agent systems), oncology and clinical informatics
• Competitive salary and excellent research infrastructure (e.g. access to the Alps cluster with 10k high-end GPUs - within SwissAI projects)
• Our group is actively engaged with the ETH AI Center and SwissAI initiative, giving our group members access to this vibrant and world-class AI community

We look forward to receiving your online application with the following documents (concatenated into one PDF):

• CV (including a list of most significant publications)
• Bachelor and Master transcripts
• Motivation letter (motivation & fit to the project and the host lab)
• Letters of recommendation (if available, also just a list of names that can be queried for letters of recommendation will suffice)

Further information about our research group can be found on our Website. Questions regarding the position should be directed to [email protected](no applications).

Please note that we exclusively accept applications submitted through our online application portal. Applications via email, social media, or postal services will not be considered. We plan to collect applications for 1 month (until July 19), and reserve the option to extend this window.