Key Responsibilities

• Clinical Data & Disease Modeling

o Trusted Data Space Exploration: Collaborate with internal Infrastructure teams and external vendors to spearhead the exploration and construction of a clinical trusted data space. Define scientific and compliance requirements to ensure secure and efficient utilization of sensitive clinical data for research.

o Clinical Multi-omics Analytics: Lead the end-to-end lifecycle of clinical and multi-omics data (e.g., RNA-Seq, proteomics, clinical phenotypic data), including data acquisition, rigorous cleaning, standardization, and advanced feature analysis to uncover high-value biological insights.

o Disease & Target Modeling: Leverage processed multi-omics features to analyze disease pathogenesis, develop QSP/disease models, and identify novel therapeutic targets or predictive biomarkers for patient stratification.

• AI Support for Target Research and Clinical platforms

o Support the development and maintenance of internal biologics platforms, integrating developability prediction and antibody optimization tools.

o Partner with AI engineering teams to guide the development of specialized AI agents for therapeutic target research. Act as the domain expert to define biological logic, workflows, and acceptance criteria for automated literature mining, hypothesis generation, and target validation.

o Infrastructure Support: Maintain necessary high-performance computing pipelines to support bioinformatics tasks and model training (focusing on application-level support rather than underlying cloud architecture).

o Build and optimize customized AI models to address specific biological questions in the drug discovery process.

Qualifications

• Education&Experience

o Master’s degree in Bioinformatics, Computational Biology, or a related field.

o Minimum of 3 years of algorithmic development experience within the biotech or pharmaceutical industry.

o Proven track record in processing clinical/multi-omics data and developing disease models for drug outcome prediction.

• Core Skills

o Clinical Data Engineering: Extensive experience in cleaning, processing, and integrating clinical and multi-omics data; proficiency in feature engineering and handling missing or noisy data in real-world clinical datasets.

o Algorithm Development: Proficient in ML/DL frameworks (PyTorch, Keras, XGBoost) and QSP modeling methodologies; ability to build disease model/target discovery/prediction systems from scratch.

o Programming: Mastery of Python, and Linux/Bash environments with strong engineering and data mining capabilities.

o Omics Background: Deep understanding of NGS data analysis (WES, RNA-Seq) and bioinformatics workflows, with the ability to correlate molecular data with clinical outcomes.

o Business Insight: Fundamental understanding of the biologics R&D process and the ability to translate complex biological questions into robust mathematical models.

o Soft Skills: Rigorous logical thinking and professional humility, with the ability to collaborate effectively with other teams.