The Impact You'll MakeAs a Staff Machine Learning Scientist , you will be contributing to dynamic short to medium term projects that derisk novel capabilities with potential to reshape Recursion's roadmap. You will conceptualize and and directly contribute to the development of novel ML models across a range of data types including vision, genomics, other Omics and clinical data that will power a diverse range of use cases in drug discovery. By leveraging your experience in machine learning, drug discovery, software engineering, and data, you will:Conceptualize and scope 3-6 month high impact projects for cross-functional workstreamsDirectly contribute to and coordinate execution of these projectsMentor other data and machine learning scientistsInterface with a diverse range of collaborators, including company leadership (VP+)Work within dynamic, interdisciplinary teams of biologists, product managers, data and ML scientists, software engineers, and moreBuild and curate large scale datasets for training machine learning models across multiple modalitiesDevelop new algorithms and architectures and train large models on these datasetsExplore properties of the resulting representation model on a range of benchmarksDevelop new benchmarks for interpreting how models are behavingWork with other teams to support deploying these models to Recursion's platformLocation:Toronto HQ | SLC HQ | expected to be on-site 50% of the timeThe Team You'll Join You will be joining Inception Labs, a research and development team within Recursion. This team is a cross-functional group of exceptional biologists, engineers, product managers, machine learning scientists, computational biologists, and data scientists. Together, we are working to prove out novel technologies including new biological assays and data modalities, statistical and ML techniques, and computational approaches for multimodal data. This team works rapidly on a project-by-project basis to either prove or disprove the value and feasibility of these new ideas and approaches. Recursion has built a unique dataset (over 1 million unique biological perturbations profiled in a high-dimensional biological assay, making up nearly 20 PB of highly-relatable data) and a unique approach to phenotypic drug discovery using our inference-based Recursion Map to predict tens of billions of relationships between disease models and therapeutic candidates. Additionally, we've generated additional large-scale Omics datasets to complement our phenomics data. Recently, Recursion has also gained access to large numbers of anonymized patient records including medical imaging and molecular profiling artifacts to guide our understanding of disease mechanisms. The capabilities you bring to the Inception Labs team will help us scale our machine learning models using these and other data sets to develop net-new capabilities that don't currently exist!The Experience You'll NeedExpert knowledge in machine learning theory & practice and its applications to challenges in biological or medical science including the ability to:Ideate and scope net-new impactful ML-based projects that can impact drug discoveryCoordinate with stakeholders and teammates as well as contribute directly to execute on projectsDevelop net-new algorithms and architectures, particularly leveraging self-supervised and multi-modal learningExperience with one of but ideally multiple types of biological data (microscopy, histology, transcriptomics, clinical data)Run quick and focused computational experiments evaluating project feasibilityWork closely with biologist to develop new training and benchmarking datasetsInterpret and develop benchmarks for assessing model performanceTools: PyTorch, NumPy, Pandas, GCP, Hybrid Cloud, Linux, CUDA, Docker, Kubernetes, BigQuery, large scale distributed systemsHow You'll be SupportedYou will join an interdisciplinary team that's having a major impact internally and externally You will contribute to conference publications and have the opportunity to attend major ML conferencesYou will collaborate with other cutting edge teams at Recursion, including Valence Labs at Mila in Montreal#LI-EP1
