Sr. Principal / Distinguished ML Scientist, Autonomous Science for Cell Biology

Your Impact at LILA

Lila is building a platform where AI and automation co-evolve to solve the hardest problems in medicine. Within Life Science AI (LSAI), we are launching 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 that integrate deep biological expertise with foundation modeling and agentic systems.

We are seeking a Sr. Principal or Distinguished ML Scientist to be the founding senior ML Scientist on this team. This is a 0→1 leadership-grade role with a clear, complementary partnership at the top of the team. You will co-develop the team's scientific direction with the VP of AI for Cell Biology, and you will own the integration of cell-biology research with Lila's central autonomous-science platform — the foundation-model, agentic-systems, and experimental-automation infrastructure that closes the loop between AI reasoning and the lab. Where the VP carries cross-functional implementation (applications, commercial activities, and the operating interfaces with our autonomous-lab and product teams), you carry the technical architecture by which cell-biology research becomes part of Lila's broader autonomous-science capability.

Cell- and tissue-scale biology sits at an open frontier of AI for science. The field has produced strong specialist models across sub-domains — single-cell foundation models, structural prediction, perturbation response, cellular imaging, pathway and ligand–receptor inference — but the architecture for system-level reasoning that ties these together, grounds them in experimental reality, and produces actionable mechanism-of-action hypotheses is still being defined. We have a working point of view on that architecture and on how Lila's autonomous-science platform extends to cellular biology; you will refine, challenge, or replace it. The architectural choices you make alongside the VP will shape what Lab-in-the-Loop autonomous science looks like at cell and tissue scale.

This is a senior role for someone operating at the frontier of generative AI applied to biology, with the scientific judgment to define research strategy and the technical depth to drive end-to-end the architecture that integrates cell-biology research with our autonomous-science platform.

What You'll Be Building

• Co-develop the scientific direction. Partner with the VP to define the cell-biology research agenda end-to-end — from problem formulation through architecture, large-scale training, evaluation, and integration into Lila's Lab-in-the-Loop autonomous-science lifecycle.
• Own integration with Lila's central autonomous-science platform. Architect how cell-biology research feeds into and benefits from Lila's foundation-model, agentic-systems, and experimental-automation infrastructure. This includes the cross-program inference architecture; the data, reasoning-trace, and experimental-protocol specifications shared with our central AI Research and autonomous-lab teams; the contribution path of cell-biology research into Lila's broader autonomous-science capability; and the working partnerships with those central teams that make integration coherent.
• Lead the foundation-model and integration architecture. Own the technical choices that turn cell-biology data into mechanism-grounded scientific inference — including which models to train or adapt at scale, which strong specialists to integrate from the field (single-cell foundation models, structural prediction, perturbation, spatial, imaging, pathway), and how to compose them into end-to-end reasoning systems. The design space is open and the architectural bet is yours to shape with the VP.
• Lead agentic discovery. Build systems that plan, execute, and reason over scientific experiments — closing the loop between models, our autonomous experimental platform, and wet-lab feedback to accelerate cellular and tissue biology research.
• Own the cross-program evaluation architecture. Design and steward the benchmarks and evaluation methodology that gauge progress across the team's cell-biology research programs and that show how those gains accrue to Lila's broader autonomous-science capability over time. Benchmarks you stand up here outlive any single program and become part of Lila's standing scientific evaluation suite.
• Translate between biology and ML. Frame complex cellular, multi-cellular, and tissue-scale biology questions as well-defined ML problems, and interpret model outputs alongside experimental scientists and computational biologists.
• Carry the scientific narrative. Internally, set technical standards for scientific excellence, reproducibility, and rigorous benchmarking, and grow scientific coherence across the team's research programs. Externally, represent Lila's AI for Cell Biology research through publications, talks, and engagement at premier scientific and ML venues.

What You'll Need to Succeed

• Education. PhD in Computer Science, Machine Learning, Computational Biology, or a related quantitative field.
• Research excellence. A track record of impact at premier venues — first- and last-author publications at ICLR, ICML, or NeurIPS (full track) and/or Nature, Science, Cell, or specialized titles (Nature Methods, Nature Biotechnology, Nature Medicine). Equivalent industry track records — production agentic-systems leadership, recognized open-source impact, or peer-reviewed contributions of comparable scope — are explicitly welcome substitutes.
• Foundation modeling and systems integration depth. Deep expertise in large-scale generative or representation-learning model architectures, with hands-on experience training and adapting them at scale, and hands-on experience integrating multiple specialist models into end-to-end reasoning systems. The role's architectural bet sits across both capabilities; the right balance is yours to shape.
• Agentic and autonomous-science systems experience. Demonstrated work on agentic, active-learning, or closed-loop systems — particularly those that plan, decide, or reason over scientific or experimental processes, and ideally those coupled to automated or autonomous laboratory infrastructure.
• Cell- and tissue-biology fluency. Working fluency across multiple cell-biology data modalities — single-cell omics, perturbation biology, spatial profiling, cellular imaging, multi-omics — with experience designing computational experiments grounded in biological reality at cell-and-tissue resolution. We are looking for breadth across the cell-and-tissue stack, not narrow expertise in a single sub-modality.
• Co-authorship of research strategy. Demonstrated ability to co-develop and drive research agendas in partnership with senior peers, in early-stage or greenfield environments, from problem framing through publication and deployment. This role is interdependent with the VP by design; pure independent program leadership is not what we are hiring for.
• Cross-functional collaboration. Strong track record of collaboration across experimental scientists, computational biologists, and central AI/ML or platform-engineering teams. Bilingual translation between cell biology and ML is a daily activity.
• Tooling. Expertise in modern ML frameworks (PyTorch, JAX, or TensorFlow).

Bonus Points For

• Experience composing specialist biology models (e.g., sequence-to-function models, single-cell foundation models, structural prediction models, perturbation models, imaging models) into multi-step reasoning systems.
• Experience with closed-loop or Lab-in-the-Loop workflows where computational predictions drive experimental decisions and experimental results retrain or retune models.
• Experience with large-scale distributed training infrastructure (cloud or on-prem clusters) — useful but not required, since this role primarily consumes rather than operates such infrastructure.
• Contributions to open-source ML tools, frameworks, or benchmark datasets for scientific (especially cell-biology) applications.
• Track record of recruiting, mentoring, or growing high-performing ML research talent.
• Experience presenting strategic technical visions to executive stakeholders or external scientific communities.