About the BIIE
The Botnar Institute of Immune Engineering (BIIE) is a new interdisciplinary research institute dedicated to innovation in immune engineering. Founded in 2025 through a generous endowment from Fondation Botnar, the BIIE supports scientists in taking on some of the world’s most challenging problems in immunology and global health. The institute unites experts across immunology, biomedicine, bioengineering, computational biology, artificial intelligence, and machine learning, creating a unique multidisciplinary environment with a mission to make a lasting impact and to train future leaders in immune engineering. BIIE’s cutting-edge research spans systems immunology, synthetic biology, and computational immunology – all underpinned by advanced scientific computing and data analysis.
Position Overview
The Botnar Institute of Immune Engineering (BIIE) in Basel is seeking a mid-career Machine Learning Scientist to lead the computational efforts for one of its flagship programs. The flagship program specializes in generating large-scale antibody and T-cell receptor (TCR) datasets for machine learning applications in immune receptor discovery. In this role, you will oversee a small computational team and drive the development of innovative machine learning models for protein design and immune engineering. You will work at the intersection of sequence-based and structure-based protein modeling, leveraging state-of-the-art techniques in deep learning and cloud computing to advance antibody and TCR discovery.
Tasks
* Technical Leadership: Lead the design and implementation of ML-driven protein modeling projects, including rapid prototyping of novel algorithms for biological sequence and structure analysis. You will plan and execute experiments with state-of-the-art models to push the boundaries of protein function prediction and design.
* Protein Design & Analysis: Develop and apply machine learning methods to predict protein function from sequence and structure, and to design novel proteins (especially antibodies and TCRs) with desired properties. This includes projects focused on protein structure prediction, antibody-antigen interaction modeling, affinity maturation, epitope/paratope analysis, and assessing developability and immunogenicity of engineered proteins.
* Data Integration & Pipeline Development: Oversee the curation and integration of large-scale sequence and structural datasets (internal and public) to train and validate models. Ensure robust data pipelines and collaborate with software engineers to maintain high-quality, reproducible analysis workflows, from data preprocessing to model deployment.
* Collaborative Research: Work closely with automation and wet-lab scientists in iterative design-build-test cycles. Guide the design of antibodies/TCRs for experimental testing, incorporate experimental feedback into model refinement, and integrate AI/ML approaches into existing antibody engineering workflows. Collaborate with cross-functional teams (e.g. protein engineers, bioinformaticians) to translate computational predictions into real-world therapeutics.
* Team Management and Mentoring: Supervise and mentor a small team of junior scientists or engineers. Provide technical guidance, code reviews, and support career development. Foster a collaborative team culture where unblocking colleagues and knowledge sharing are prioritized. Coordinate team efforts and ensure timely delivery of project milestones.
* Communication and Reporting: Communicate progress, results, and recommendations clearly to stakeholders. This includes writing reports and presenting findings in group meetings, seminars, or external conferences. As a lead scientist, you will also interface with institute leadership to align on project goals and contribute to strategic decisions for the group.
* Innovation and Continuous Learning: Stay current with the latest research in machine learning, bioinformatics, and protein engineering. Explore emerging techniques (e.g. protein language models or generative diffusion models) and evaluate their potential to improve project objectives. Proactively propose and implement novel solutions (technical or algorithmic) that keep the group at the cutting-edge of AI-driven protein design.
Requirements
Education
Ph.D. in Computer Science, Computational Biology, Bioinformatics, Biophysics or a related field. A strong background at the interface of machine learning and biology is essential. Candidates should have a few years of postdoctoral or industry experience beyond the PhD, demonstrating the application of ML to biological problems. A solid publication record or equivalent research impact (e.g. influential projects or tools) is expected for this role.
Experience:
* Machine Learning Expertise : Demonstrated expertise in modern machine learning and deep learning techniques. Hands-on experience developing and training deep neural networks from scratch and fine-tuning existing models. Proficiency with deep learning frameworks (such as PyTorch and/or TensorFlow) and libraries for data science (Pandas, scikit-learn, etc.) is required. Familiarity with large-scale models (e.g. transformer-based protein language models or diffusion models for protein design) is a plus.
* Computational Biology & Protein Modeling : In-depth knowledge of computational protein science. Experience with sequence-based and structure-based protein modeling tools is highly sought after. For example, proficiency in using or customizing tools like AlphaFold, RoseTTAFold, Rosetta, ProteinMPNN, or RFDiffusion for protein structure prediction and design is expected. Exposure to antibody-specific modeling (e.g. antibody structure prediction, paratope-epitope mapping) and general bioinformatics tools (BLAST, Biopython, PyMOL for visualization) will be beneficial.
* Domain Knowledge : Strong understanding of protein engineering and developability considerations for therapeutic proteins (e.g. stability, aggregation, immunogenicity). Prior experience in antibody or TCR discovery is a major advantage – for instance, knowledge of antibody sequence databases, immune repertoire analysis, or lab techniques for antibody characterization. The ideal candidate can connect biological insights with ML modeling, ensuring that computational work is biologically relevant and translatable.
* Programming and Data Skills : Excellent programming skills in Python (scientific computing and scripting). Competence in data handling — ability to work with large-scale datasets (omics, sequencing, structural data) and perform data analysis, visualization, and pipeline automation. Experience with version control (Git/GitHub) and working in Linux/Unix environments is beneficial for collaborative code development.
* Cloud Computing & HPC : Experience with cloud platforms (AWS, GCP) and high-performance computing environments for running large experiments. This includes familiarity with cloud-based GPU/TPU instances, cluster job scheduling, and containerization (Docker/Singularity) to deploy and scale models. Ability to optimize workflows for efficiency and cost-effectiveness in the cloud is expected.
* Teamwork and Leadership : Proven ability to work productively in interdisciplinary teams. Excellent communication skills and a collaborative mindset are essential. You should have experience leading projects or small teams, including coordinating with diverse experts (wet-lab scientists, engineers, data specialists). A mentorship-oriented attitude is important – we value leaders who help train others and build an inclusive, innovative team culture.
* Problem-Solving and Innovation : A passion for tackling challenging scientific problems with AI. The candidate should be creative, curious, and self-motivated, with the determination to drive projects to completion. Evidence of innovation – such as developing a novel algorithm, pipeline, or insight in prior work – will distinguish the candidate. We seek someone who stays abreast of new developments and can quickly learn and integrate new methods for the group’s benefit.
Preferred Qualifications (Bonus Skills)
* Immunology Domain Experience : Familiarity with immunological data and concepts, such as B-cell receptor/TCR repertoire analysis, antibody engineering (e.g. humanization, affinity maturation techniques), or immunoassay data interpretation. While not strictly required, the ability to contextualize machine learning results within the domain of immune engineering will allow for a bigger project impact.
* Track Record of Impact : A history of leading successful ML projects in biotech or academia, evidenced by high-impact publications, patents, or contributions to products and pipelines. Experience in translating computational research into tangible outcomes (like a new therapeutic candidate or a deployed tool) is highly valued.
* Project Managemen t: Skills in project planning and resource management. For instance, experience in managing project timelines or coordinating collaborations will be useful in this role (the institute encourages scientific leadership and may offer opportunities for you to direct projects or funding initiatives).
Joining BIIE as a Lead Machine Learning Scientist offers a unique opportunity to have a profound impact on a growing institute at the forefront of immune engineering innovation. You will be a key contributor to groundbreaking research in immune engineering, directly enabling discoveries that could transform healthcare and save lives.
If you are an experienced ML scientist with a passion for science and innovation, we encourage you to apply and join us in building a world-class computing environment at BIIE. Together, we will empower researchers to push the boundaries of immune engineering and make a real difference in the world.