Shape Therapeutics is a biotechnology company developing breakthrough gene therapy technologies to treat the world’s most challenging diseases. ShapeTX gene therapy platform comprises RNAskip™, RNAfix™, and RNAswap™ payload technologies, next-generation tissue-specific AAVid™ delivery technology, and SquareBio, a solution to scalable gene therapy manufacturing based on industrialization of human stable cell lines. At the core of these technologies reside ShapeTX AI analytic platform, where data drives decisions in building technology today to enable gene therapies of tomorrow. ShapeTX is committed to data-driven scientific advancement, passionate people, and a mission of providing life-long cures to patients. Shape Life!
At ShapeTX, we are a dynamic team of professionals who are dedicated and passionate about making cures a reality. Through diversity of thought, scientific knowledge, professional rigor and focus we are merging cutting-edge science with extensive drug development expertise to unlock cures to many debilitating diseases.
Shape Therapeutics is headquartered in Seattle, Washington with a satellite site in Cambridge, Massachusetts.
ShapeTX is looking for a highly motivated individual with strong interest and experience in data science and Next-Generation Sequencing (NGS) to join the fast-growing Analytics and Informatics team as a Machine Learning Scientist, Genomics. In this role, the successful candidate will develop and apply novel statistical learning techniques across diverse molecular and NGS datasets to further revolutionize our gene editing, delivery, expression, and manufacturing methods under development. The ideal candidate will have experience developing and applying unsupervised, semi-supervised, and supervised statistical modeling approaches to high dimensional datasets, as well as general familiarity with NGS components and genomic data structures. This individual will have the unique opportunity to throw themselves headlong into refining statistical and deep learning techniques to advance novel gene therapies that treat serious human genetic diseases.
Roles and Responsibilities:
- Design and implement statistical and machine learning (ML) analyses that rigorously test biological hypotheses in gene editing, delivery, and complex disease.
- Interface with experimentalists to understand data structure and incorporate appropriate methodologies to ensure accuracy and facilitate decision-making.
- Utilize and cross-compare diverse analytical strategies using quality control metrics to troubleshoot and optimize computational workflows for disparate data types.
- Write and maintain clearly documented code, and effectively collaborate and iterate for further optimization.
- Operationalize deployment of validated, predictive models to inform experimental design and therapeutic prioritization.
Qualifications and Requirements:
- Doctorate, or Master’s degree with over six years of experience, in ML, Statistics, Genomics, Computer Science, Data Science, or a related discipline.
- Ability to work both independently and collaboratively in a team-science environment.
- Ability to tackle challenges with a problem-solving, can-do attitude, with a desire to work in a fast-paced, start-up environment.
Skills and Experience:
- Passionate about building tools and executing strategies that optimally leverage novel data types to address biological hypotheses through statistical inference.
- Takes initiative to identify, develop, and optimize innovative ML approaches for predictive models of gene editing outcomes.
- Demonstrated proficiency in a programming language (Python, Bash, R) and common data science tools (pandas, tidyverse and out-of-core tools).
- Fluency with at least one deep learning framework for neural network inference (e.g. TensorFlow-Keras, PyTorch).
- Experience with statistical modeling and inference using large, biological datasets and NGS.
- Experience with cloud-based services (e.g. AWS) and version control systems (e.g. Git).
- Capacity to simultaneously progress multiple projects involving different data types and structures.
- Intellectual curiosity, superb attention to detail, meticulous organizational skills, consistent follow-through, effective and proactive communication, and collaborative spirit with a team-player mindset.
- Experience in molecular biology, NGS experimental protocols, or high-throughput screening is a plus; as is knowledge of protein biology, RNA biology, neurobiology, or genetic diseases.
If the notion of analyzing novel NGS and molecular datasets towards providing an end-to-end gene therapy solution for millions suffering worldwide from rare genetic disorders motivates you like it does us, we’re very excited to have you join us!