About the job

Location: Berlin, Germany

Start Date: As soon as possible / by arrangement

ABOUT DAiNA

DAiNA is a precision-oncology company focused on enabling personalized cancer treatment for individual patients. We combine comprehensive molecular tumor data including genomics, transcriptomics (bulk, single cell and spatial), proteomics and epigenetics, with AI-driven analysis. Our platform connects multi-omic profiling with functional ex-vivo tumor models and personalized liquid-biopsy monitoring, creating a continuous workflow from biopsy and treatment selection through to therapy monitoring and adaptation. We also operate GMP manufacturing to produce individualized N=1 therapeutics. In short, we help physicians make more informed, personalized treatment decisions based on high-dimensional molecular tumor data.

For more information, visit: www.daina.com

THE ROLE

As Applied AI / ML Lead Engineer, you will help build DAiNA’s applied AI capability at the core of our precision-oncology platform. Your focus will be on translating modern machine learning, large language models and retrieval-augmented generation into robust, secure and clinically relevant software systems. You will design and implement AI-driven workflows that support molecular data interpretation, clinical reporting, knowledge retrieval, decision support and digital-twin development. A key part of the role is to ensure that sensitive patient and molecular data can be processed in a secure, compliant and auditable environment, with strong control over model behavior, data provenance and system performance.

WHAT YOU’LL DO

• Design, build and operate applied AI/ML systems for DAiNA’s precision-oncology platform

• Develop and maintain retrieval-augmented generation (RAG) architectures for molecular data interpretation, clinical reporting, literature/knowledge retrieval and internal decisionsupport workflows.

• Build robust components for document ingestion, chunking, embedding, vector search, reranking, grounding, citation handling and evaluation.

• Deploy and operate open-weight and/or self-hosted models in secure cloud or isolated environments, reducing unnecessary dependency on external AI providers for sensitive patient data.

• Evaluate and fine-tune domain-specific models where this adds measurable value, using reproducible training, validation and benchmarking workflows.

• Integrate AI components into DAiNA’s reporting layer, data platform and broader computational oncology workflows.

• Develop guardrails, audit trails, hallucination-control strategies and human-in-the-loop review mechanisms for sensitive scientific and clinical use cases.

• Lead and coordinate a small distributed technical team or external specialists across architecture, retrieval, model serving, fine-tuning and AI evaluation.

• Work closely with bioinformatics, data engineering, clinical, wet-lab and management stakeholders to ensure AI systems address real workflow needs.

WHAT YOU BRING

• Strong software engineering background with hands-on experience building productiongrade ML, AI or LLM-based systems.

• Practical experience with large language models, including open-weight model families

• Deep practical understanding of RAG systems, including embeddings, vector databases, chunking strategies, retrieval, re-ranking, grounding and evaluation.

• Experience with MLOps practices such as model/version management, automated evaluation, monitoring, logging, deployment and reproducibility.

• Strong communication skills and the ability to explain technical trade-offs clearly to scientific, clinical and management stakeholders.

NICE TO HAVE

• Experience in healthcare, biotech, diagnostics, pharma or another regulated environment.

• Experience with clinical or biomedical data, including molecular profiles, omics data, pathology reports, clinical notes, literature, treatment guidelines or real-world evidence.

• Familiarity with digital twin approaches, computational oncology, cancer biology or personalized medicine.

WHY DAINA

• Employer contributions toward private health insurance or supplementary health coverage, as well as pension or retirement savings.

• Hybrid model with ~60% of working time expected on-site and the rest remotely, depending on team and business needs.

• Performance-based bonus opportunity, depending on company and individual performance.

• A personal development budget for conferences, courses, certifications, and training.

• The opportunity to work directly on real patient cases and help shape a first-in-class precision-oncology platform

• A proactive, collaborative team with fast decision-making and strong ownership of your domain.