SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 268,000 - 384,000 / annual
Lila Sciences is building Scientific Superintelligence to solve major challenges by combining large-scale automated data generation with AI. The company operates an AI Science Factory that executes the scientific method autonomously across medicine, materials, and energy.
You will be a Senior ML Scientist focused on translational biology, connecting AI and automation work to human medicine. Your core mission is building systems that assess whether a clinical program's proposed biology holds up in reality. Three key questions drive the work: Is the mechanism well supported by evidence? Does the mechanism operate in actual patients? Is the trial designed to test that mechanism?
You will not evaluate programs individually but will build scalable systems that do this work. You'll draw on mechanistic models and structured biological evidence generated by the team and ground them in human data. Your judgment sets the specification and standard for these systems, and you will build evaluations—including outcome-verifiable forecasts scored against information available at prediction time—to assess their effectiveness.
Key responsibilities include: building systems that assess mechanistic support for clinical programs using structured biological evidence; analyzing human genetic, expression, cohort, and trial data to determine whether a mechanism is present and rate-limiting in patient populations; evaluating trial design (endpoints, biomarkers, dosing, eligibility criteria) for alignment with proposed mechanisms; building outcome-verifiable forecasts with proper evidence boundaries; collaborating with ML scientists, mechanism scientists, and engineers; communicating findings to technical and cross-functional audiences; and supporting external visibility through publications and community engagement.
You will run your own analyses and evaluations, interpret results yourself, and work in reproducible pipelines. The role emphasizes evidence judgment, mechanistic reasoning, and making expert judgment reproducible through structure rather than case-by-case expertise.
REQUIREMENTS:
- PhD in a computational discipline (translational bioinformatics, computational biology, biomedical informatics, biostatistics, epidemiology, machine learning, or related) with research centered on human biomedical data
- Hands-on ML and data analysis for translational medicine; fluent in Python with substantial experience analyzing human genetic, multi-omic, cohort, trial, or real-world data in reproducible pipelines
- Mechanistic reasoning about therapeutic interventions; able to articulate how an intervention works, what evidence would establish each step, and where human evidence supports or undercuts it
- Clinical development fluency; working knowledge of trial design, endpoints, biomarker strategy, eligibility and enrichment criteria
- Evidence judgment and systems instinct; able to reason about what was knowable when and resist hindsight bias; interested in making judgment reproducible through structure and evaluation
BONUS EXPERIENCE:
- Human genetics for target identification and validation (common/rare variant evidence, QTL, expression data)
- Biomarker development, patient stratification, companion diagnostics, or enrichment strategy
- Clinical trial datasets, real-world data, or observational cohort analysis
- Evaluating language models or agents on scientific judgment tasks with contamination and memorization controls
- Survival analysis, competing risks, calibration, or forecasting methodology
- Structured evidence frameworks (GRADE, systematic review protocols, assessment rubrics)
