Principal / Sr. Principal BioML Scientist

Your Impact at LILA

Lila is building a platform where AI and automation co-evolve to solve the hardest problems in medicine. Within Life Sciences AI (LSAI), we are standing up a new AI for Cell Biology team to develop autonomous-science capabilities for cellular and tissue biology, spanning single-cell omics, perturbation biology, spatial profiling, imaging, genetics, and multi-modal experimental data.

We are seeking a Principal or Sr. Principal BioML Scientist to be a co-architect of how Lila's autonomous-science platform changes cell biology and to own the applied and translational BioML charter that turns those platform capabilities into real-world therapeutic impact. The team's ML lead owns core model strategy and inference architecture; the Engineering lead owns platform infrastructure; this role adds the applied scientific perspective into platform shape: deciding what closed loops are worth running, what kinds of scientific questions become tractable when AI and lab automation co-evolve, and what evidence standard turns a model output into an experimental decision. The platform isn't something this role consumes; it's something this role helps build, from the applied science side. This role grows and leads the team's applied science footprint: a group of domain-embedded scientists working across disease areas and therapeutic modalities (cell therapy, nucleic-acid delivery, small molecule). The initial applied focus is target identification as the entry point into cell-biology-grounded therapeutic discovery, with the scope broadening over time as the team and the platform mature.

This is a senior individual contributor role today and a team-leadership role within twelve months. We are deliberately lean to start, so the first months involve hands-on execution — using the team's AI platform to deliver real computational biology that downstream therapeutic teams and external partners consume. That hands-on phase is short-lived by design: the right candidate brings the scientific judgment to set the bar, the recruiting instincts to attract strong scientists into the embedded roles, and the leadership track record to grow them once they land. Alongside this charter, the role contributes to the team's benchmarking framework with research and engineering leads, mentors research pod leads, and serves as scientific liaison into product and partnership scoping.

What You'll Be Building

• Grow and lead the applied science footprint, anchoring a team of domain-embedded scientists across disease areas and therapeutic modalities; recruit, mentor, and develop those scientists as the team scales.
• Co-architect the AI-for-Cell-Biology platform's scientific direction, partnering with the AI/ML Science and Engineering leads to shape how AI, lab automation, and closed-loop experimentation together change how cell biology is done — what closed loops to run, what cycle times and evidence thresholds matter, what kinds of scientific questions become tractable that weren't before.
• Own the applied and translational BioML charter, translating foundational AI-for-cell-biology research into platform-deployable tools and partnership-grade capability.
• Anchor an initial applied program in target identification and evaluation in support of next-generation therapeutic discovery as the entry point, broadening the applied scope over time across disease areas and therapeutic modalities.
• Pioneer applied use of the platform, being among the first to use Lila's autonomous-science capabilities to do cell biology in new ways: running closed-loop experiments, composing AI and lab-automation in ways no one has tried yet, and generating both scientific results and the product-shaping feedback that tells the platform team what to build next. While the team is lean, this is also where the technical bar gets set for incoming scientists.
• Mentor research pod leads and set operating norms for the pod-lead cohort, growing scientific judgment and execution standards across pods.
• Shape the team's evaluation framework and scientific bar alongside research and engineering leads by owning what makes a benchmark biologically meaningful, what evidence threshold turns a model output into an experimental decision, and what counts as the platform delivering real new science rather than just well-scored predictions.
• Serve as scientific liaison to product and partnership functions, bringing technical-feasibility judgment into external collaboration scoping.
• Represent the team's research externally through publications, talks, and engagement with therapeutic-platform and computational-biology communities.

What You'll Need to Succeed

• Education. PhD in Computational Biology, Computational Genomics, Machine Learning, or a related quantitative field.
• Research excellence. Track record of impact in computational cell biology or target identification at premier venues, with first- or last-author publications at Nature, Science, Cell, specialized titles (Nature Methods, Nature Biotechnology, Nature Medicine), and/or ICLR, ICML, or NeurIPS. Equivalent industry impact through deployed platforms or applied research of comparable scope is welcome.
• Vision for AI-driven science. A clear, defensible point of view on how AI, lab automation, and closed-loop experimentation together change how cell biology is done — and excitement about being a co-architect of that change at platform scale, not just an applier of existing tools. Track record of having pushed for or led a meaningful methodological shift in how science gets done is a strong plus.
• Team-building and leadership track record. Demonstrated experience hiring, growing, and leading computational scientists — whether as a manager, tech lead, or senior IC who has built de facto teams around them. Comfortable transitioning from IC execution to people leadership as the team scales.
• Applied computational cell biology depth. Deep scientific fluency across multiple cell-biology modalities (single-cell omics, perturbation biology, spatial profiling, imaging, and adjacent data types), with hands-on experience using modern ML/AI methods to extract biological insight from these data.
• Target identification as an initial applied focus. Demonstrated work in computational target identification or closely adjacent applied programs (e.g., disease-mechanism mapping, perturbation-driven discovery), strong enough to anchor the team's initial applied program in this area.
• Translation to deployed capability. Experience translating computational research into deployed capability that downstream teams or external partners consume, including building evaluations that hold up in deployment rather than only against held-out research benchmarks.
• Mentorship of senior scientists. Track record growing scientific judgment in research scientists, postdocs, or pod leads, including peers and near-peers, not only direct reports.
• Cross-functional collaboration. Strong collaboration across experimental scientists, computational biologists, platform engineering, and product or business stakeholders.

Bonus Points For

• Experience scoping or supporting external partnerships where technical-feasibility judgment shapes the deal.
• Experience with Lab-in-the-Loop or closed-loop workflows where computational predictions drive experimental decisions.
• Experience working alongside or within therapeutic-modality teams (cell therapy, nucleic-acid delivery, small molecule).
• Contributions to open-source tools, benchmarks, or datasets for applied computational cell biology — including but not limited to target identification.
• Experience in early-stage or 0→1 environments where applied and research charters had to be built in parallel.