Intern, Machine Learning & Protein Engineering (MS or PhD)

Key Skills

JAX framework, Machine learning techniques, Python Programming, PyTorch, R Programming, Statistical modeling, TensorFlow

Job Description

Calico is seeking an intern to join the Calico Applied Machine Learning (CAML) team. To succeed, you will need to be an enthusiastic team player, detail-oriented, extremely organized and comfortable working on complex problems. In this position you will develop and apply sequence design and protein folding models to problems of practical interest. You will identify and solve specific problems relating to the scalability and accuracy of these models. The successful candidate will work closely with members of the machine learning team on advancing the state-of-the-art in protein language modeling, structure prediction, and design.

Responsibilities: 

• Work within an interdisciplinary team to implement and extend machine learning algorithms for protein sequence and structure modeling and evaluate their performance on large protein datasets
• Quickly iterate and improve on technical contributions in-house and from protein modeling literature
• Contribute easily maintainable, robust, and flexible code for model training and pipelines 
• Interpret and communicate results to both team members and a wider audience of interdisciplinary scientists

Position requirements:

• Currently pursuing a MS or PhD degree in computer science, computational biology, statistics, applied mathematics, or related field
• Experience working with Python and PyTorch, TensorFlow, JAX or related ML frameworks
• Knowledge of modern machine learning techniques, including their strengths and shortcomings
• Track record of applying machine learning methods to solve problems at scale
• Strong analytical and quantitative problem solving skills
• Detail-oriented and organized
• Strong teamwork and communication skills
• Self-motivated with a “can-do” attitude
• Ability to work on-site in the South San Francisco office (pursuant with Calico’s return-to-site hybrid work policies)

Nice to have:

• Experience with language models for biological sequence data, structure prediction models such as AlphaFold, ESMFold, OmegaFold, etc. and/or inverse folding models for de novo protein design
• Experience applying machine learning to problems in the physical sciences, especially biology or chemistry
• Familiarity with high performance computing clusters, cloud computing tools, or similar

About our Program:

Calico’s internship program is a paid 12-week program over the summer for students interested in understanding the fundamental science of aging and finding treatments for the associated and intractable diseases. Working in a collaborative environment and fully embedded in one of our labs/teams, Calico interns tackle a unique project under the mentorship of at least one of our scientists or engineers. Students from all schools, and students who identify with a demographic that is underrepresented within the technology, data science, and healthcare industries are encouraged to apply. This includes but is not limited to Black, Latinx, Native American, students with disabilities, veterans, and non-binary people.

Program Features:

• 3-month summer timeline
• In-person experience at our offices in South San Francisco
• Matching with at least one Calico mentor
• Group supplemental activities weekly featuring guest speakers, Senior Leadership spotlights, and discussion groups on aging science, our drug development approach, and more
• End-of-summer company-wide project showcase and poster session
• Competitive compensation ($40 - $65/hour) and monthly living expenses stipend