Role Summary
Lexeo is at an inflection point where AI and advanced analytics can materially accelerate decision-making across discovery, development, and operational execution. This Sr. Director will set direction and deliver applied AI/ML solutions across internal workflows and externally facing outputs, ranging from R&D insights to partner-ready analyses, while partnering closely with scientific teams and, when needed, external vendors/partners to solve real problems. This role is intentionally hands-on and outcome-driven: a leader who can build, validate, and operationalize models using real-world biopharma data to raise the signal-to-noise ratio in small or unstructured datasets (including synthetic control arm approaches where appropriate).
Key Responsibilities
AI/ML Strategy + Delivery
-
Define and execute Lexeo’s applied AI/ML roadmap across discovery and development, prioritizing use cases that improve speed, quality, and decision confidence.
-
Deliver solutions that are internal-only (e.g., scientific decision support, operational forecasting) and those that are generated internally but external-facing (e.g., partner-ready analyses (regulatory dossiers, briefing books, protocols etc.), validated dashboards, and decision materials).
-
Establish best practices for model lifecycle management (validation, documentation, monitoring, retraining), especially where outputs influence scientific decisions or regulated workflows.
Advanced Analytics + Predictive Modeling
-
Lead development and selection of appropriate ML approaches (e.g., XGBoost, Random Forest, SVMs, and other advanced models) based on problem framing, data constraints, interpretability needs, and deployment context.
-
Build and oversee predictive analytics using real-world data, including robust evaluation design, bias/variance trade-offs, and performance monitoring.
Small Data Excellence + Synthetic Controls
-
Apply techniques to amplify signal-to-noise in smaller datasets (e.g., regularization, Bayesian methods, hierarchical modeling, augmentation, multimodal integration, careful feature engineering, uncertainty quantification).
-
Guide strategy for synthetic control arms and comparable approaches (as appropriate), ensuring methodological rigor, transparency, and fit-for-purpose use in decision-making.
Drug Discovery / Translational Partnership
-
Translate drug discovery and translational questions into testable analytical hypotheses; partner with bench scientists to design data capture that enables strong modeling.
-
Serve as a bridge between scientific teams and data/engineering, ensuring solutions are scientifically credible and operationally adoptable.
Cross-functional Enablement + Platform Integration
-
Partner with stakeholders across R&D, CMC, Clinical, Safety, and IT/Security to implement scalable data pipelines and AI-enabled workflows.
-
Contribute leadership to current and emerging initiatives such as AI workflow automation/database buildouts and analytics agents that leverage enterprise platforms (examples already in motion include CMC AI automation, MaxisAI clinical database/AI efforts, and AI work to ingest historical data into Dataverse/Fabric for agent-based analysis; integration work such as a Benchling AI API initiative may also be in scope depending on priorities).
External Partner/Vendor Leadership
-
Liaise with external partners to evaluate tools, define statements of work, and deliver solutions—while ensuring knowledge transfer and sustainable internal ownership.
Operational Excellence
-
Improve internal processes through automation and analytics, focusing on measurable impact (cycle time, error reduction, throughput, decision latency).
-
Establish practical governance for data quality, documentation, and fit-for-use standards aligned with the realities of biopharma environments (including where regulated practices apply).
-
A prioritized AI/analytics roadmap tied to measurable R&D outcomes; clear ownership and delivery cadence.
-
2–4 production-grade analytics solutions adopted by teams (internal and/or external-facing outputs as needed).
-
A repeatable approach for small datasets and high-noise signals; documented modeling standards and review practices.
-
Strong partner engagement model: vendors/partners used strategically, with internal capability building and durable outcomes.
Required Qualifications
-
Advanced degree in a quantitative or scientific discipline (PhD strongly preferred; MS with exceptional experience considered).
-
10+ years of relevant experience across applied data science/ML in life sciences/biopharma (or adjacent domain with direct drug discovery translation), including 5+ years leading teams and influencing senior stakeholders.
-
Deep familiarity with advanced ML methods (including XGBoost, Random Forest, SVMs) and the judgment to select and justify the right tool for the job.
-
Demonstrated experience building predictive models with real-world, imperfect datasets and delivering them into production or decision workflows.
-
Proven ability to improve processes and operationalize analytics—moving beyond prototypes to adoption.
-
Strong cross-functional communication: can partner with scientists, engineers, and executives; can explain model performance and limitations clearly.
Preferred Qualifications
-
Direct experience in drug discovery, translational research, and/or R&D decision support (target ID/validation, MoA, biomarker strategy, preclinical data integration).
-
Experience with small data strategies, causality-aware thinking, and synthetic control arms or closely related methodologies.
-
Experience operating in regulated/quality-sensitive environments and building documentation practices that scale (particularly relevant where validation and traceability are required)
-
Familiarity with enterprise data platforms and modern analytics stacks (lakehouse/warehouse patterns, feature stores, MLOps, model monitoring).