Overview In this role you will develop AI/ML models for translational safety across discovery, preclinical, clinical, and real-world data. You will partner with translational scientists and data teams to identify safety biomarkers, de-risk compounds, and enable faster, evidence-based go/no-go decisions. You will advance cross-domain AI reasoning and Foundation models linking discovery to RWE, driving safer, more efficient drug development.
Compensation / Benefits- Retirement plan and 401(k) matching
- Paid vacation (vacation 120 hours/year)
- Sick leave (40-56 hours/year by state)
- Parental leave (480 hours)
- Bereavement leave (240 hours)
- Volunteer leave (32 hours/year)
Responsibilities- Design, build, and validate AI/ML solutions for translational safety using multimodal data across discovery, preclinical, clinical, and RWE domains
- Develop predictive models and AI reasoning frameworks for safety, biomarker discovery, and clinical outcome prediction
- Integrate high-dimensional datasets (imaging, omics, EHR, claims) to derive novel insights for de-risking safety signals
- Establish scientific validation, benchmarking, explainability, and regulatory-grade documentation
- Prototype Foundation-model connectors and AI-enabled reasoning to link discovery, preclinical, clinical, and RWE for closed-loop learning
- Collaborate with translational scientists, toxicology, clinical safety, PV, Knowledge Engineering, Data Products, and external partners to prioritize use cases
- Communicate methods and results clearly to diverse audiences; maintain reproducible code and versioned repositories
- Deliver scientifically credible AI capabilities to enable earlier safety and efficacy outcome predictions
- Support regulatory and cross-functional reviews with robust model evidence
- Assist in operationalizing models and building reusable assets for R&D programs
Key requirements- AI/ML experience in life sciences (industry or post-doc)
- 2+ years post-PhD or 3-5 years relevant industry experience
- Domain expertise in translational science, biomarker discovery, safety assessment or related drug-discovery areas
- Strong programming ability (Python) and experience with AI frameworks (PyTorch or TensorFlow)
- Knowledge of ML/DL methods (Transformers, CNNs, graph networks, self-supervised learning, multi-instance learning)
- Experience with multimodal representation learning, foundation models, LLMs/GraphRAG, and multimodal data fusion
- Experience analyzing imaging, multi-omics, and real-world clinical data at scale
- Capable of scientific reasoning, rigorous analysis, and clear communication
- Nice-to-have: regulatory-grade model evidence and production-ready model assets
- Analytical thinking
- Scientific rigor
- Strong written and oral communication
- Python
- PyTorch
- TensorFlow
