Senior ML Scientist, Biological Systems
Job description
Your Impact at LILA
Lila is constructing a platform where artificial intelligence and automation co-evolve to address the most complex challenges in medicine. Within the Life Science AI (LSAI) division, the focus is on developing autonomous-science capabilities for cellular and tissue biology. This work spans single-cell omics, perturbation biology, spatial profiling, imaging, genetics, and multi-modal experimental data. These domains integrate deep biological expertise with foundation modeling and agentic systems.
The organization is seeking a Senior Machine Learning Scientist to help execute this vision. The role involves translating the direction of Autonomous Life Science AI into working architectures, workflows, and evaluation methods. These systems must enable AI to reason rigorously about biological hypotheses, propose experiments, incorporate evidence, and accelerate discovery.
This is a hands-on scientific and technical role. The individual will operate at the intersection of machine learning, biological reasoning, agentic systems, and experimental design. The right candidate will be comfortable formalizing the representation of scientific knowledge, managing uncertainty, updating belief with evidence, and executing automated cycles of life science discovery.
What You'll Be Building
- Build autonomous life science systems that connect AI reasoning, biological evidence, experimental design, and automated execution.
- Translate the broader Autonomous Life Science AI vision into concrete architectures, workflows, prototypes, and production-quality research systems.
- Develop methods for representing hypotheses, uncertainty, evidence, and scientific arguments to enable robust machine reasoning.
- Apply Bayesian reasoning, epistemology, and scientific methodology to design AI systems capable of proposing, testing, and revising biological hypotheses.
- Design agentic workflows that plan experiments, reason over results, and close the loop between computational predictions and automated laboratory feedback.
- Partner with ML scientists, experimental scientists, automation teams, and platform teams to ensure systems are biologically grounded and experimentally actionable.
- Build evaluation frameworks for autonomous discovery systems, including benchmarks for reasoning quality, hypothesis generation, evidence integration, and experimental utility.
- Contribute to the technical roadmap for autonomous life science research systems and help elevate the scientific rigor of the team's approach.
What You'll Need to Succeed
- Hold a PhD in Computer Science, Machine Learning, Computational Biology, Statistics, Biology, or a related quantitative field.
- Maintain a strong research track record in machine learning, AI for science, computational biology, or probabilistic modeling.
- Demonstrate a deep understanding of scientific reasoning, experimental design, uncertainty, and evidence integration.
- Have experience building or researching systems that reason over complex scientific, biological, or experimental data.
- Possess a strong foundation in modern ML methods, with hands-on experience in frameworks such as PyTorch, JAX, or TensorFlow.
- Ability to translate biological questions into computational and ML problems, and to translate ML system behavior back into scientific terms.
- Exhibit strong technical judgment, with the ability to operate in open-ended research settings where the right architecture, abstraction, or evaluation method is not yet obvious.
- Show excellent collaboration skills across AI, biology, automation, and platform teams.
Bonus Points For
- Experience with Bayesian modeling, probabilistic programming, causal inference, or formal methods for reasoning under uncertainty.
- Experience building agentic, active-learning, closed-loop, or autonomous-science systems.
- Familiarity with biological data modalities such as single-cell omics, perturbation data, imaging, spatial profiling, genetics, or multi-omics.
- Experience designing systems that generate, rank, test, or revise scientific hypotheses.
- Background in philosophy of science, epistemology, scientific methodology, or formal argumentation.
- Experience communicating complex technical concepts to diverse audiences.
---
About the role
You architect and ship core reasoning capabilities for life science AI. In this position, you will own the full cycle from problem framing to validated biological insight. The role demands rigorous method design, transparent uncertainty handling, and steady collaboration with wet lab teams. You will turn high-level biological questions into executable ML experiments that meaningfully advance discovery.
Key facts
What you'll do
Architect modular experiment planning agents that coordinate hypotheses, data, and lab interfaces.
Design representation systems for uncertainty and evidence, enabling rigorous biological argumentation.
Guide evaluation framework creation, including benchmarks for reasoning quality and hypothesis utility.
Build partner-oriented workflows that align platform teams with experimental biology constraints.
Implement closed-loop systems where automated results refine scientific models iteratively.
Champion scientific methodology, translating biological questions into testable ML formulations.
Develop integration patterns connecting foundation models with cellular and imaging data sources.
Steer roadmap priorities to strengthen autonomous discovery rigor across the team.
Requirements
Hold a PhD in a quantitative field such as computer science, biology, or statistics.
Maintain a strong research record in machine learning or AI for science domains.
Demonstrate a deep grasp of experimental design, uncertainty, and evidence integration.
Have hands-on experience with probabilistic modeling and modern ML frameworks.
Translate biological problems into computational tasks and interpret outcomes scientifically.
Operate effectively in ambiguous, open-ended research environments.
Collaborate fluently across automation, experimental, and platform engineering groups.
Nice to have
Experience with Bayesian modeling, causal inference, or formal argumentation methods.
A track record building agentic, closed-loop, or autonomous science systems.
Familiarity with omics, imaging, or spatial profiling data modalities.
A background in philosophy of science or scientific methodology.