Senior Scientist II, Computational Discovery Science

Jobtailor

California (MO)

On-site

USD 150,000 - 190,000

Full time

3 days ago

Be an early applicant

Application generator

Stand out for this role — generate a tailored resume and cover letter in about a minute.

Get past ATS filters

Job summary

Tempus is seeking a PhD-level data scientist to apply analytical methods to multi-modal data, identifying targets in cancer sub-populations and leveraging real-world data for pattern discovery.

You will join a cross-functional team including modeling labs, genomics, data science, and medical leads, driving translational work and publishing scientific findings.

Qualifications

PhD in a quantitative discipline with publication record.
4+ years using genomic and multimodal data with ML in cancer.
Proficient in R, Python, and SQL.
Strong cancer genomics/immunology knowledge.
Experience analyzing single-cell RNA-seq and spatial transcriptomics.
Excellent written and verbal communication; able to present to diverse audiences.
Multidisciplinary project team leadership experience.
Familiar with PDO models for target ID and MOA.
Experience with early-stage drug development and biomarker discovery.
Client-facing experience; thrives in a fast-paced environment.

Responsibilities

Apply analytical methods to multi-modal data to identify targets in patient sub-populations.
Use in silico methods on Tempus Real-World Data to find molecular and clinical patterns.
Leverage multimodal data to create joint embeddings for robust clustering.
Utilize the LLM-orchestrated Tempus Loop Agent to autonomously prioritize work.
Collaborate with modeling labs using organoid data to identify targets.
Lead translational or real-world evidence research projects.
Work with cross-functional teams across R&D, product engineering, labs, data science, and medical teams.
Communicate plans and outcomes to leadership, partners, and stakeholders.
Present findings to diverse audiences and external partners.
Author abstracts, posters, and peer-reviewed publications in multimodal AI and drug discovery.

Skills

Python

SQL

Machine Learning

Genomics

Immunology

Team leadership

Communication

Pandas

NumPy

SciPy

Scikit-Learn

Jupyter Notebooks

RStudio

tidyverse

ggplot

Git

Docker

AWS

R package dev

Education

PhD in quantitative discipline

Tools

Python

SQL

Pandas

NumPy

SciPy

Scikit-Learn

Jupyter Notebooks

RStudio

tidyverse

ggplot

Git

Docker

AWS

Job description

Utilize novel analytical methods applied to multi-modal data—such as genomic, imaging, and clinical data to identify targets in patient sub-populations
Apply in silico methodologies to Tempus Real-World Data (RWD) to identify molecular, biological, and clinical patterns associated with specific patient populations
Leverage multimodal data to compress complex data into joint embeddings, enabling robust clustering of patients and the identification of novel molecular subtypes
Utilize the LLM-orchestrated Tempus Loop Agent architecture to autonomously prioritize
Partner with Tempus’ modeling lab, using data from CRISPR and cell perturbation experiments in patient-derived organoids to identify and validate novel targets
Independently execute complex translational or real-world evidence research projects integrating molecular and clinical data from the Tempus multimodal data platform
Work closely with cross-functional teams across R&D and the broader Tempus organization, including product engineering, clinical genomics labs, data science, and medical teams
Communicate scientific and technical plans and outcomes to cross-functional project and senior leadership stakeholders, internal and external partners
Present scientific findings clearly and meaningfully to diverse external stakeholders and non-technical audiences
Author abstracts, posters, and peer-reviewed publications illustrating the value of multimodal analysis and AI in drug discovery

Requirements

PhD in a quantitative discipline (e.g., Bioinformatics, Computational Biology, Data Science) or Life Sciences with a strong computational publication record
PhD with 4+ years of work experience leveraging genomic and multimodal data with machine learning approaches to address questions in complex diseases, especially cancer
Proficient in R, Python, and SQL
Strong understanding of Cancer, Genomics, and/or Immunology
Extensive prior experience analyzing genomic data and running statistical/machine learning models
Excellent written and verbal communication skills, with the ability to present complex information clearly and persuasively to diverse audiences
Multidisciplinary project team leadership experience and a demonstrated ability to lead complex projects
Familiarity with the use of patient-derived organoid (PDO) models for target identification and validation, biomarker discovery, and identifying a drug’s mechanism of action (MOA) or preclinical proof-of-concept (POC)
Experience with early-stage drug development, including target discovery and biomarker identification
Experience analyzing single-cell RNA sequencing and spatial transcriptomics
Proficient in computational biology packages and environments including Pandas, NumPy, SciPy, Scikit-learn, Jupyter Notebooks, RStudio, tidyverse, ggplot, Git, Docker, and AWS
Experience with R package development
Comfort in a client-facing role with prior consulting and/or client-facing experience
Ability to thrive in a fast-paced environment and willingness to shift priorities seamlessly

Core Competencies

Demonstrates expertise in leveraging genomic and multimodal data through machine learning to identify targets in complex diseases, particularly cancer. Proficient in statistical analysis and communication of scientific findings to diverse audiences.

Highest-signal resume keywords