Director, AI Scientist & Product Lead – Drug Discovery

About Us:

Structure Therapeutics develops life‐changing medicines for patients using advanced structure‐based and computational drug discovery technology. The company’s platform combines the latest advancements in visualization of molecular interactions, computational chemistry, and data integration to design orally available, superior small molecule medicines that overcome current limitations of biologic and peptide drugs. We are advancing a clinical‐stage pipeline of differentiated treatments focused on chronic diseases with high unmet need, including cardiovascular, metabolic, and pulmonary conditions.

With offices in California and Shanghai, Structure Therapeutics has the benefit of being at the center of life science innovation in both the US and China and capitalizing on the strengths of each geographic location.

Position Summary:

We are seeking a Director, AI Scientist & Product Lead, Drug Discovery to lead the strategy, development, and adoption of artificial intelligence capabilities for our discovery organization in China. This is a player-coach role for a leader who can move fluently among science, data, technology, and product execution. The role works directly with structural biologists, medicinal and computational chemists, biologists, pharmacologists, and other research colleagues to turn important scientific problems into trusted, usable AI products.

The Director will own the Discovery AI product portfolio from opportunity identification and scientific problem definition through design, prototyping, launch, adoption, and value realization. The role requires sufficient technical depth to engage hands-on in data and modeling strategy, experimental design, evaluation, and prototype development, together with the product judgment and leadership presence to align diverse stakeholders and deliver capabilities that improve research decisions.

This individual will be a senior scientific and product partner to local research teams and a core member of the global AI organization. They will collaborate closely with AI scientists, engineers, product leaders, data specialists, and technology partners in the United States to create secure, scalable, and reusable enterprise AI capabilities. Although drug discovery is the role's primary mandate, the Director will help shape shared platforms and methods that can support translational medicine, preclinical development, CMC, clinical development, medical affairs, and commercialization.

Job Responsibilities:

Lead the Discovery AI Product Strategy

- Develop and own a multi-year AI product vision, roadmap, and portfolio for drug discovery, aligned with research strategy and measurable scientific and business priorities.

- Partner with discovery leaders and scientists to identify high-value opportunities across target and mechanism assessment, structural biology, hit identification, lead generation and optimization, compound design, assay interpretation, developability, knowledge management, and portfolio decision-making.

- Translate scientific needs into clear product hypotheses, user requirements, data requirements, success metrics, validation plans, and delivery roadmaps.

- Prioritize initiatives based on scientific value, technical feasibility, data readiness, time to evidence, risk, scalability, and potential for adoption; recommend when to build, buy, partner, or stop.

- Maintain a balanced portfolio of near-term workflow improvements, strategic data and platform capabilities, and scientifically ambitious applications of AI.

Provide Scientific & Technical Leadership

- Shape AI/ML approaches for small-molecule discovery, including methods that may use molecular representations, sequence and structure information, functional and biochemical assay data, SAR, docking, biophysical evidence, imaging, literature, and internal scientific knowledge.

- Guide the development and evaluation of predictive, generative, retrieval, and agentic capabilities while selecting methods appropriate to the scientific question and available evidence.

- Work hands-on where it adds the most value—for example, interrogating data quality, defining modeling cohorts and labels, reviewing analyses and code, prototyping approaches, evaluating model behavior, and interpreting results with scientists.

- Establish rigorous evaluation strategies, including leakage-resistant and scaffold-aware validation, prospective testing, benchmark comparisons, calibrated uncertainty, applicability-domain assessment, and analysis of failure modes.

- Ensure that model outputs are scientifically interpretable and traceable, with the supporting evidence needed for researchers to make informed decisions.

- Promote closed-loop learning by capturing experimental decisions and positive and negative results in forms suitable for governed analysis and model improvement.

Own Products from Discovery Through Adoption

- Lead cross-functional product teams through discovery, definition, design, build, validation, launch, and continuous improvement.

- Co-design workflows with end users so AI capabilities fit naturally into scientific practice and complement expert scientific judgment.

- Define product and scientific success measures such as prospective enrichment, prediction quality and calibration, cycle-time reduction, decision confidence, user adoption, and impact on experimental productivity.

- Partner with software, data, ML, cloud, security, and enterprise-architecture colleagues to convert prototypes into reliable, supportable products.

- Drive pilot and validation studies with explicit baselines, preregistered decision criteria where appropriate, and clear paths from proof of concept to scaled use.

- Lead change management, training, feedback collection, and product iteration to ensure that released capabilities are understood, trusted, and routinely used.

Serve as the AI Partner to China Discovery Research

- Build trusted working relationships with structural biology, chemistry, pharmacology, DMPK, computational science, and research leadership teams.

- Facilitate multidisciplinary problem-solving sessions that connect biological hypotheses, chemical design, structural evidence, experimental constraints, and quantitative methods.

- Surface local scientific needs and data realities early, represent them in global product decisions, and ensure solutions work in the research environment.

- Act as a translator across scientific, technical, and executive audiences, communicating both the potential and the limitations of AI with clarity.

- Develop internal AI fluency through coaching, demonstrations, office hours, communities of practice, and hands-on collaboration with project teams.

Connect the Global AI Organization

- Operate as an integrated member of the global AI team, sharing ownership of architecture, product standards, reusable components, evaluation methods, and delivery practices.

- Coordinate effectively across multiple time zones, maintaining clear decisions, documentation, interfaces, and accountability.

- Identify where discovery solutions can benefit from or contribute to shared enterprise capabilities such as scientific knowledge systems, governed data products, model services, agent frameworks, evaluation infrastructure, identity and access controls, observability, and human-review patterns.

- Contribute discovery expertise to AI initiatives spanning translational medicine, preclinical development, CMC, clinical development, medical affairs, and commercialization while protecting the focus and delivery capacity required for discovery.

- Build productive relationships with external technology and scientific partners when they provide differentiated value, and support technical and scientific due diligence.

Uphold Responsible AI, Data & Scientific Governance

- Embed data stewardship, privacy, intellectual-property protection, cybersecurity, reproducibility, and appropriate documentation throughout the product lifecycle.

- Partner with legal, compliance, quality, IT, and scientific colleagues to determine proportionate controls for each use case.

- Preserve human accountability for high-consequence scientific decisions and define explicit evidence and governance gates before increasing automation.

- Monitor product and model performance after launch, including data drift, model limitations, scientific failure modes, adoption barriers, and unintended use.

- Set a high standard for honest scientific communication, distinguishing exploratory signals from validated findings and avoiding unsupported claims of AI impact.

Leadership

- Personally contribute hands-on to the hardest scientific and product questions while creating the structure, clarity, and momentum that enable others to succeed by bringing scientists along.

- Lead multidisciplinary teams through influence and shared purpose, including colleagues who do not report directly to this role.

- Coach scientists and technical contributors in product thinking, experimental rigor, responsible AI, and effective cross-functional collaboration.

- Help define the longer-term capability and talent needs for discovery AI and support selective team growth, partnerships, and community building.

Qualifications:

- PhD in computational chemistry, cheminformatics, computational biology, structural biology, bioinformatics, computer science, statistics, applied mathematics, or a related discipline; or equivalent advanced expertise demonstrated through relevant industry accomplishments.

- 5 or more years of relevant industry experience, including significant leadership of AI-enabled drug-discovery products or programs; exceptional candidates with a different experience profile will also be considered.

- Experience integrating chemistry, biological assay, structural, and translational data to support compound design or prioritization.

- Experience with prospective model validation and design–make–test–analyze cycles, including collaboration with medicinal chemists and experimental scientists.

- Familiarity with modern molecular ML, generative chemistry, structure-based methods, scientific foundation models, knowledge graphs, retrieval-augmented generation, or agentic scientific workflows.

- Experience building governed scientific data products and integrating with research platforms such as electronic lab notebooks, compound registration systems, assay repositories, chemical-design platforms, or scientific knowledge bases.

- Experience converting prototypes into production-grade capabilities in partnership with ML engineering, software engineering, data engineering, and cloud-platform teams.

- Experience evaluating external vendors, research collaborations, or technology partnerships and managing sensitive scientific data appropriately.