Scientist II/ Senior Scientist, BioML

Your Impact at LILA

Lila is building a platform where AI and automation work together to solve the hardest problems in biomedicine. Within Life Sciences AI (LSAI), we are building the loop where AI, automation and experimental biology co-evolve.

We are seeking a Scientist II/ Senior Scientist, BioML to work at the intersection of mechanistic modeling and experimental design. Helping build the biological mechanism layer of that loop: reasoning systems that take a mechanistic hypothesis apart into what must be true for it to hold, judge what the existing evidence actually settles, and identify what remains open. You will encode what good mechanistic adjudications look like and build the evaluations that measure a system against them.

Then you will help close the loop: at Lila, when the evidence to ground or test a system does not exist, we generate it. You will design experimental campaigns that anchor these systems in real measurement, and own the analysis of the data that comes back. The core of this role is to decide what is worth measuring and closing that loop.

The ideal candidate brings strong hands-on experience in computational biology, BioML, or applied ML for biological data, and can partner effectively with experimental scientists, ML researchers, and platform engineers. This person will help define tractable scientific questions, design rigorous analyses, interpret model outputs in biological context, and contribute to workflows that connect computational predictions with experimental decisions.

This is an individual contributor role for a scientist who wants to drive meaningful applied work in a fast-moving, interdisciplinary environment. The role will emphasize execution, scientific judgment, and cross-functional collaboration rather than group leadership or owning the broader platform direction.

What You'll Be Building

• Encode mechanistic reasoning into systems, and build the evaluations that hold them to it. Turn how a good scientist decomposes a hypothesis — what must be established, in what order, what distinguishes the live alternatives — into structured frameworks and reasoning workflows that operate without you in the loop. Define what a good answer is, and score whether a system reached it for the right reason rather than a plausible-sounding one.
• Analyze the biological data that grounds these systems. Hands-on analysis of single-cell, perturbation, proteomics imaging, and genetic data: build the pipelines that turn raw measurement into model-ready evidence, run the quality control and annotation-stability analyses that determine how much weight a given fact should carry, and produce the quantitative results the reasoning layer depends on.
• Design experimental campaigns and close the loop on them. Specify what to measure, in which contexts, at what precision and scale — both to anchor these systems in real data and to generate outcome-verified cases they can be trained and scored against. Analyze what comes back, update the assessment, and say what changed.
• Build outcome-verifiable benchmarks and set the evidence standards behind them. Including retrodiction sets that score a system on predicting a documented outcome from pre-decision evidence only, with the evidence boundary enforced. Define what counts as direct versus inferred evidence, and when a computational prediction may substitute for a measurement.
• Co-design with ML scientists and engineers, and with experimental scientists. Shape evaluations so they measure decision quality rather than apparent reasoning quality, and ensure outputs carry usable uncertainty.
• Communicate results completely. Publish and present to scientific, engineering, and therapeutic audiences, including the parts of a result that do not support the conclusion people want.

What You'll Need to Succeed

• PhD in Computational Biology, Bioinformatics, Computational Genomics, Biostatistics, Machine Learning, or a related quantitative field, with research centered on biological data.
• Strong hands-on computational and data-analysis depth. Fluent Python; substantial experience analyzing high-dimensional biological data (single-cell omics, perturbation screens, imaging-based proteomics, or genetics) in reproducible, version-controlled pipelines. You will run your own analyses and evaluations and interpret them yourself.
• Mechanistic biology fluency. Able to reason about a pathway or drug mechanism step by step: what is rate-limiting, what would be observed if it were, what evidence distinguishes the alternatives, and what a given assay can and cannot establish. This is what you will be encoding.
• Evidence judgment, and the instinct to make it into a system. Demonstrated ability to assess whether data support a claim and to reason about what was knowable when — combined with an interest in making that judgment reproducible by something other than you, through structure, schemas, or evaluation.
• Clear communication. Ability to explain methods, assumptions, results, and limitations to both technical and interdisciplinary audiences.

Bonus Points For

• Deep analysis experience in at least one of: perturbation screens, single-cell omics, imaging-based proteomics, or functional genomics.
• Depth in immune cell biology, cell therapy, or targeted delivery — receptor engagement, trafficking, or effector function.
• Experience with lab-in-the-loop or closed-loop workflows, active learning, or experiment selection.
• Experience evaluating language models or agents on scientific judgment tasks, including contamination and memorization controls.
• Experience designing or applying structured evidence frameworks, curated resources, or controlled vocabularies that other people depend on.