Sr Data Scientist
South San Francisco, CA, United States
FULLY REMOTE
PLEASE DO NOT RESUB PREVIOUSLY PRESENTED (SHORTLISTED, REJECTED JOB SEEKERS from prior request AMAGJP00012397)
OPEN MARKET RATE - Hiring Manager has budget up to ***/hour Max for the *** hourly bill rate*****(***/hour is to ***).
1 YEAR WITH EXTENSION UP TO 3 YRS
**Please reference top 3 skills and day to day responsibilities in the job description in the request.
Interview Process: 1st Phone screen, 2nd round take home exam and prepare for remote presentation of past work for 45min.
The Computational Biology group in the Clinical Biomarkers & Diagnostics (CBD) department at *** is seeking a highly motivated Sr data scientist to join our team and contribute to develop machine learning modeling and prediction pipelines using multi-modal biomarker data from clinical trials.
Responsibilities
• Maintain and develop in-house endpoint association and modeling/prediction pipeline that use cutting edge machine learning methodologies to develop biomarkers of clinical response and resistance, extend analytical capabilities of biomarker platform
• Define and implement Bioinformatics strategy and protocol-driven configuration layers of biomarker platform for *** studies
• Perform pan-study analysis to find biomarkers that are predictive of safety and efficacy endpoints.
• Serve as a subject matter expert and implementation lead for application of open-source R and python Client modeling libraries to clinical trial data and real world data (from external partners, publicly available data or consortia data).
• Work cross-functionally with stakeholders in Research and Development.
• Communicate findings and insights and present them to the team.
Basic Qualifications
Doctorate degree and 1-2 years of scientific experience
OR
Master's degree and 3-5 years of scientific experience
OR
Bachelor's degree and 5-7 years of scientific experience
Preferred Qualifications
• PhD or MS in Bioinformatics, Mathematics, Statistics, Computer Science, or a related quantitative field.
• Significant experience in bioinformatics, applied mathematics and/or statistics to analyze multi-modal, multi-dimensional and large-scale biological datasets including whole exome sequencing, RNA-seq, and high-throughput proteomics data.
• Familiarity of clinical bioinformatics domain and associated technologies, real world biomarker data
• Working experience of data QC, data preprocessing, feature selection, model building and deployment.
• Fluency in both Python and R programming languages and associated DevOps tools (version control, Client Ops).
• Ability to work in a highly matrixed environment and drive scientific and technical innovation collaboratively with other group members and with *** research community.
• Strong written and oral communication skills, self-motivation, independence, and leadership.