Computational Biologist Summer Intern - Protein Machine Learning
: Pleasanton, CA
At 10x Genomics, accelerating our understanding of biology is more than a mission for us. It's a commitment. This is the century of biology, and the breakthroughs we make now have the potential to change the world.
We enable scientists to advance their research, allowing them to address scientific questions they didn't even know they could ask. Our tools have enabled fundamental discoveries described in over 3000 peer-reviewed publications across multiple application areas, including cancer, immunology, and neuroscience.
Our teams are empowered and encouraged to follow their passions, pursue new ideas, and perform at their best in an inclusive and dynamic environment. The innovations and discoveries that we enable together will lead to better technologies, better treatments, and a better future.About The Role
The Computational Biology group at 10x Genomics is looking for an outstanding intern to work with us in the Summer of 2022. This person will be responsible for the research and development of machine learning approaches and workflows to explore antibody and T cell receptor data and will contribute to 10x's antigen receptor sequencing and discovery product portfolio. This internship provides an opportunity to explore large and cutting-edge antibody and T cell receptor single cell datasets.
The ideal candidate will apply their experience and knowledge in machine learning to develop techniques to encode, study, and reason about molecules in the adaptive immune repertoire. Being able to explain and communicate your work to stakeholders and team members with varying degrees of familiarity in this area is essential. Prior experience with common ML frameworks (TensorFlow, PyTorch, Keras, etc.) is a requirement, and an ability to combine novel and existing approaches into reproducible pipelines is a plus. Experience with biological problems (and, particularly, immunology) would be ideal but is not required.What You Will Be Doing
To Be Successful In This Role, You Will Need
- Develop algorithms and approaches to encode protein sequences into efficient structures for machine learning
- Design and implement new algorithms and methods for analyzing and learning from single-cell immune repertoire data to support possible discovery and therapeutic applications
- Quantify and explore the performance of conventional statistical and modern ML methods on immune repertoire data from a wide array of experimental conditions
Also, We'd Like To See
- 1+ years as a PhD student in computational biology or other quantitative field (e.g., physics, mathematics, computer science, statistics, electrical engineering or similar)
- Ability to communicate complex scientific ideas clearly and work well in a team environment
- A combination of mathematical depth with a healthy respect for the imperfections inherent in real-world data
- Programming ability in any language (one or more of Python/R/Rust/C/C++ preferred)
- Experience with machine learning methods and frameworks
- Ability to prototype and implement protein learning algorithms
- Experience in analyzing and visualizing complex data sets using Python (single-cell or spatial genomics data is a plus)
- Experience or a completed project using one or more of:
- NGS data tools (e.g., bwa, samtools, GATK)
- Immune receptor tools (enclone, Immcantation, scRepertoire, OPIG software, or similar)
- Large open-source protein or nucleotide sequence datasets
- Does the internship have to be over the summer?
- Depending on the match between the candidate, the problem(s) and their scope, and other logistics, there is potentially flexibility regarding the time of the year and duration of the internship. However, we would like the internship to be at least 3 months long, since it is hard to make a significant contribution towards difficult scientific challenges in less time than that.
- I just started learning how to use common ML frameworks. Should I apply for this position?
- We are looking for a candidate who can hit the ground running building prototypes and frameworks that ingest NGS-derived nucleotide and amino acid sequencing data. We'll teach you all the biology that you might need but you should already be up to speed on the computational foundations.
At 10x Genomics, accelerating our understanding of biology is more than a mission for us. It is a commitment. This is the century of biology, and the breakthroughs we make now have the potential to change the world.
We enable scientists to advance their research, allowing them to address scientific questions they did not even know they could ask. Our tools have enabled fundamental discoveries across biology including cancer, immunology, and neuroscience.
Our teams are empowered and encouraged to follow their passions, pursue new ideas, and perform at their best in an inclusive and dynamic environment. We know that behind every scientific breakthrough, there is a deep infrastructure of talented people driving the life sciences industry and making it possible for scientists and clinicians to make new strides. We are dedicated to finding the very best person for every aspect of our work because the innovations and discoveries that we enable together will lead to better technologies, better treatments, and a better future. Find out how you can make a 10x difference.
Individuals seeking employment at 10x Genomics are considered without regards to race, color, religion, national origin, age, sex, marital status, ancestry, physical or mental disability, veteran status, gender identity, or sexual orientation.
10x does not accept unsolicited applicants submitted by third-party recruiters or agencies. Any resume or application submitted to 10x without a vendor agreement in place will be considered unsolicited and property of 10x, and 10x will not pay a placement fee.