Director/Senior Director, Molecular Discovery

Lila Sciences•Cambridge, MA

1d•$202,400 - $323,400

About The Position

The Director, Molecular Discovery is responsible for ensuring our autonomous science platform reliably and repeatedly delivers validated small-molecule drug candidates against designated targets at increasing speed. The platform generates and tests hypotheses at superhuman scale, and you ensure that process translates into real, high-quality compounds that advance toward the clinic. This role leans heavily into the AI and computational side of our workflow: you will be accountable for throughput, quality, and the operational health of the discovery engine, working hand-in-hand with AI scientists, computational chemists, and platform engineers to diagnose bottlenecks, close feedback loops, and continuously improve how the platform performs.

Requirements

Ph.D. in medicinal chemistry, computational chemistry, chemical biology, or a closely related discipline.
12+ years of experience in small molecule drug discovery from the computational, medicinal chemistry, or program leadership side with at least 5 years in a senior role closely involved in advancing compounds from hit-to-lead through candidate selection.
Demonstrated involvement in programs that delivered clinical candidates, with enough proximity to compound progression decisions to own them whether from the computational, medicinal chemistry, or program leadership side.
Deep fluency in medicinal chemistry principles, you may not have practiced bench medchem, but you understand SAR, synthetic tractability, and the multiparameter tradeoffs at the core of lead optimization (potency, selectivity, ADMET, PK, safety) well enough to guide them or define systematic decision frameworks for them.
Operational mindset, experience running discovery programs with clear metrics, milestones, and accountability structures, and a comfort level with managing throughput and efficiency alongside scientific quality.
Strong working knowledge of ADMET, DMPK, and the data packages required to advance a candidate to IND-enabling studies.
Fluency with AI/ML-driven molecular design approaches (generative chemistry, molecular property prediction, free energy methods, active learning) and the practical judgment to know when computational output is actionable and when it needs experimental validation. You don’t need to build models, but you must be a credible, hands-on collaborator with the scientists who do.
Effective communicator who can translate complex scientific and operational status into clear updates for leadership.

Nice To Haves

Direct experience with automated, high-throughput, or closed-loop discovery environments (e.g., self-driving labs, robotic synthesis and screening platforms), you've seen what it takes to make these systems produce real drug discovery output, not just proof-of-concept demos.
Experience applying computational chemistry or cheminformatics in a hands-on capacity, not just consuming model outputs, but contributing to how molecular design hypotheses are generated, scored, and prioritized.
Experience building or scaling a discovery operation from early stage, standing up assay cascades, workflows, team structures, and vendor relationships without inheriting a mature infrastructure.
Background across multiple therapeutic areas, giving you breadth in target biology and the flexibility to work across a diverse portfolio.
Process-oriented thinking: you instinctively look for ways to measure, standardize, and improve how work gets done, without letting process become bureaucracy.

Responsibilities

Own small molecule discovery programs against assigned targets, from hit identification through lead optimization and candidate nomination.
Serve as the accountable leader for discovery output setting and hitting timelines, quality benchmarks, and throughput targets across active programs.
Operate as the primary interface between the autonomous science platform and drug discovery decision-making, ensuring that what the platform produces meets the bar for potency, selectivity, ADMET properties, and developability.
Collaborate daily with AI/ML, robotics, and software engineering teams to close the loop between computational predictions and experimental results, driving continuous improvement of the platform's predictive accuracy and experimental efficiency.
Architect the components of each discovery program end to end, specifying the required assays, building or sourcing the right capabilities, and managing the scientific staff needed to execute. Define and enforce the quality standards, assay cascades, and decision criteria that govern how compounds progress through the pipeline.
Facilitate relationships with CROs and external partners for specialized studies (e.g., in vivo pharmacology, safety pharmacology, DMPK) that sit outside the automated platform.
Provide drug discovery expertise to Lila's product team for commercial partnerships, translating platform capabilities into credible value propositions for pharma and biotech collaborators.