Computational Biologist - Quantitative Methods & Target Discovery

The Opportunity 

This is an individual contributor role in Boston or Indianapolis for an experienced computational biologist who will lead analyses of multimodal biological datasets and develop methods that advance target discovery in cardiometabolic diseases. The role, in the Data Science team in CardioMetabolic Research (CMR) at the intersection of spatial and single-cell omics, causal inference, AI/ML, and functional genomics. 

The scientist in this role will independently design and implement end-to-end analyses of spatial and single-cell transcriptomic, proteomic, and metabolomic datasets, as well as functional genomics workstreams. In a team setting they will integrate results across modalities and with genetic evidence to build convergent frameworks for target prioritization, and develop predictive models to score targets, distinguish association from mechanism, and provide measures of confidence that inform portfolio decisions. 

The role also involves advancing the team's quantitative toolkit — introducing ML/AI approaches, knowledge graphs, Bayesian methods, and causal modeling where they contribute — and influencing the data architecture and analytical standards that support reproducible, scalable science. The scientist will collaborate with internal AI teams, data engineering teams, translational biology teams, statistical geneticists, and statisticians to leverage and co-develop models for drug discovery and will represent computational innovation with CMR and across the broader organization. 

This role suits a scientist who combines depth in computation with the independence to drive programs and the collaborative instinct to elevate the work of those around them. 

Who we are looking for 

Someone who loves hands-on computational work and holds strong, experience-driven experience opinions on methods. A scientist who leads through scientific influence: advising colleagues, raising analytical standards, and improving the science around them. The right candidate is drawn to connecting genetic evidence, public multi-omics data, and experimental model data to functional biology — building causal frameworks around targets and delivering measures of confidence and uncertainty that inform decisions on targets and molecules. They collaborate well with statisticians — adapting methods from other domains, co-developing new approaches, or stress-testing an existing framework to find where it breaks. They are pragmatic about methods: they know when a Bayesian model is worth the investment and when a simpler approach will do. They have enough AI and ML fluency — from agentic systems for routine tasks to foundation models and graph neural networks for complex problems — to work productively with AI teams and translate those capabilities into CMR science. Ideally, they are also motivated to build novel AI models themselves to advance drug discovery. Above all, they want to be part of a team motivated to build a robust platform together. 

What You'll Do 

Multimodal Omics & Functional Genomics 

• Design and implement single cell and spatial omics analyses integrating imaging-based, sequencing-based, and multiplexed platforms to characterize changes in tissue architecture, cellular neighborhoods, and microenvironmental as well as system-level dynamics 

• Build scalable pipelines to preprocess, QC, harmonize, and integrate large-scale spatial and molecular omics datasets, enabling discovery-ready data layers and downstream modeling 

• Hands-on end-to-end analysis of functional genomics workstreams (CRISPR screens, perturb-seq, high-content perturbation readouts) and integrate results with transcriptomic, proteomic, and pathway-level data for target prioritization 

• Ingest, develop and apply advanced AI/ML, statistical, and computational frameworks to analyze single-cell, spatial transcriptomic, proteomic, metabolomic, and multi-omics datasets at scale 

Collaboration with Discovery, Translational & Genetics teams 

• Partner closely with pre-clinical bench scientists and translational biologists in CMR to frame questions, design experiments with statistical rigor, and translate computational results into target discovery decisions 

• Consume and interpret outputs from statistical genetics and integrate them with functional and molecular data to build convergent evidence frameworks for target nomination 

• Develop predictive models that combine genetic, functional, and multi-omics evidence to score and rank targets, using causal reasoning to distinguish association from mechanism 

• Contribute to virtual patient and disease modeling approaches where multi-omics and mechanistic evidence converge to support target validation and translational hypotheses 

Computational Methods & Platform Development 

• Apply and introduce modern quantitative methods — Bayesian modeling, causal inference and causal graph modeling, mechanistic or agent-based modeling, knowledge graphs, ML/AI for target discovery and scoring — with pragmatic judgment about when each approach adds genuine value 

• Evaluate and integrate novel AI approaches for multi-omics data analysis, including graph-based methods, generative models, representation learning, and foundation models 

• Influence the design and implementation of scalable, reproducible analytical workflows for high-dimensional, multimodal data integration — contributing to the broader computational and data architecture that supports next-generation omics and ML workloads 

• Influence data architecture, pipeline design, and analytical platform standards in collaboration with data engineering and infrastructure teams 

Cross-Functional Influence 

• Work with internal AI teams, statistics teams, and Lilly Research Nucleus to leverage internally built models and co-develop new computational approaches for drug discovery 

• Champion standards in analytical rigor, reproducibility, and documentation across the computational biology community within and outside of CMR 

• Advise fellow computational biologists through code review, collaborative analysis, and shared problem-solving 

What You Bring 

Minimum requirements:  

• Ph.D. in computational biology, biostatistics, biological engineering, systems biology, applied mathematics, or a quantitative life science field, with training or research experience that combines analytical method development (Bayesian approaches, AI/ML, etc. ) with applied work in multi-omics, spatial omics, or functional genomics 

Preferred 

• 2+ years of post-doctoral or biopharma/biotech industry experience 

• Experience with spatial omics platforms (spatial transcriptomics, multiplexed imaging, spatial proteomics), single-cell RNA-seq, proteomics, metabolomics, or multi-omics data integration 

• Proficiency in Python and/or R with solid software practices — version control, documentation, reproducible workflows — and familiarity with scientific computing libraries 

• Familiarity with workflow orchestration (e.g., Nextflow), cloud-native analytical environments, and data architecture in a research organization 

• Demonstrated ability to analyze, integrate, and interpret large-scale, multimodal datasets, including experience designing scalable analytical pipelines 

• Demonstrated experience in at least two of: Bayesian methods (e.g., PyMC, Stan), causal modeling, knowledge graph approaches, ML/AI applied to biological target discovery, causal inference methods, or functional genomics data analysis at scale 

• Ability to critically interpret statistical genetics outputs and integrate them with molecular and functional data — you do not need to run GWAS, but you need to know what the outputs mean and how to use them 

• History of embedded collaboration with experimental scientists, statisticians, AI teams, or other computational scientists across organizational boundaries 

• Experience building predictive models or integrative evidence frameworks that combine genetic and functional data for target scoring 

• Experience developing or contributing to novel ML/AI models or statistical or algorithmic approaches in a biological context  

• Track record of leading through scientific influence — independently owning complex research programs, setting technical direction, and shaping priorities across teams without direct management authority 

• Strong publication record in peer-reviewed journals or ML/AI venues, reflecting methodological innovation in computational biology, multi-omics analysis, or applied machine learning