Company Description
OncoHost is a technology-driven leader in precision medicine, advancing patient outcomes through innovative, clinically validated diagnostic solutions. The company’s proprietary PROphet® platform leverages high-dimensional proteomic pattern analysis to support immunotherapy decision-making for patients with non-small cell lung cancer (NSCLC) using a single blood sample.
Validated in a large-scale, global clinical trial spanning more than 40 sites and 1,700 patients, PROphet® enables physicians to predict treatment efficacy, assess toxicity risk, and uncover biological mechanisms of resistance — supporting more informed, data-driven immuno-oncology decisions.
Role Overview
The Head of Data Science will lead OncoHost’s data science strategy, driving the development of predictive, biologically grounded AI models that support clinical decision-making. This role combines scientific leadership, hands-on technical expertise, and cross-functional influence.
Reporting to the CTO, this leader will shape the long-term data science roadmap, build and mentor a high-performing team, and ensure scientific rigor across all computational activities.
Leadership & Strategy
- Define and execute the company’s data science vision, strategy, and multi-year roadmap
- Build, manage, mentor, and develop a team of Data Scientists, including goal setting, performance evaluation, and professional growth
- Partner closely with senior management and cross-functional teams (bioinformatics, translational medicine, product, scientific affairs, commercial) to drive data-driven decision making
- Establish best practices, methodologies, and quality standards across all data science activities
Technical & Scientific Ownership
- Lead the development and deployment of advanced machine learning and statistical models to predict cancer patients’ response to treatment
- Provide technical leadership and oversight for the analysis of clinical, proteomic, and other multi-omics data
- Guide the design and define workflows for experimentation, validation, and interpretation of supervised and unsupervised learning models
- Ensure model robustness, reproducibility, validation, and statistical rigor
Cross-Functional Impact & Communication
- Collaborate with experts in proteomics, biology and clinical research to translate insights into mechanisms of treatment resistance
- Convert complex analytical outputs into clear, actionable insights for scientific, clinical, product and management stakeholders
- Lead documentation of R&D activities in high-quality technical and scientific reports
Real-World Data & Modeling Environment
- Design and validate ML algorithms with thousands of potential features and small development and validation cohorts
- Identify potential biases in the data (confounding factors, measurement biases, analytic factors, partial data etc.) and proper methods for mitigating them
- Align with restrictive regulation, to allow the utilization of the algorithms for guiding life-saving clinical treatment
- Thrive in a fast-moving, innovation-driven environment with evolving scientific priorities
Required Qualifications
- MSc in quantitative field (Computer Science, Mathematics, Physics, Bioinformatics, or related)
- PhD – an advantage
Core Technical Expertise (Mandatory)
- Proven experience leading or mentoring professional data science teams
- Strong background in Machine Learning and applied Data Science
- Expertise in supervised and unsupervised learning approaches
- Deep understanding of statistics and probability
- Proficiency in Python
Domain Expertise (Advantage)
- LLMs
- Computational biology
- Biology
Personal Attributes
- Strong interpersonal and communication skills, with the ability to operate effectively in cross-functional environments
- Independent, self-driven, and accountable
- Critical thinker with strong problem-solving abilities
- Highly motivated, curious, and able to adapt in a fast-paced setting
Work Model
- Full-time position: 5 days per week
- Hybrid Model: 4 days onsite, 1 day remote
