Senior Machine Learning Scientist, Healthcare Data

Key Skills

Data science techniques, Linux Operating system, Machine learning techniques, Statistics

Job Description

Why join Freenome?

Freenome is a high-growth biotech company on a mission since 2014 to create tools that empower everyone to prevent, detect, and treat their disease.

To achieve this mission, Freenome is developing next-generation blood tests to detect cancer in its earliest, most treatable stages using our multiomics platform and machine learning techniques. Our first blood test will detect early-stage colorectal cancer and advanced adenomas.

To fight the war on cancer, Freenome has raised more than $1.1B from leading investors including a16z, GV (formerly Google Ventures), T. Rowe Price, BainCapital, Perceptive Advisors, RA Capital Management, Roche, Kaiser Permanente Ventures, and the American Cancer Society’s BrightEdge Ventures.

Are you ready for the fight? A ‘Freenomer’ is a mission-driven employee who is fueled by the opportunity to make a positive impact on patients' lives, who thrive in a culture of respect and cross collaboration, and whose work makes a significant impact on the company and their career. Freenomers are determined, patient-centric, and outcomes-driven. We build teams around divergent expertise, allowing us to solve problems and ascertain opportunities in unique ways. We are dedicated to advancing healthcare, one breakthrough at a time.

About this opportunity:

Do you like to think deeply about data? Do you intuitively seek to understand the sources of bias, and noise? Do you learn your customer’s application well enough to be sure your work answers the right questions? Do you have expertise developing complex ML and/or deep learning models? Would you like to join a close-knit team of scientists pushing the limits of machine learning methods and changing the paradigm of healthcare from disease treatment to prevention? If that describes you, we want you on our team!

The Senior Machine Learning Scientist Healthcare Data will be responsible for developing ML and AI approaches to predictive and prescriptive modeling of disease risks, interventions and other outcomes, from large sets of healthcare data. The successful candidate will need to absorb the relevant clinical background, and to tease apart multiple layers of reporting and selection bias, among other confounders. This position requires a strong grasp of a wide variety of techniques ranging from data mining, study design, and other statistical methods to machine learning. This work is an important component of an integrated early cancer detection strategy that includes Freenome’s blood-based multi-omics molecular assays and will be applied practically to improve clinical care.

In this role, you will work closely with a small and highly collaborative team of machine learning experts, computational biologists, and data scientists, as well as a broader team of clinical and product experts seeking to change the nature of cancer by catching it early — when curative intervention is most achievable.

This role reports to the Director, Risk Modeling.

What you’ll do:

• Be self-directed and innovative contributor: research the literature, apply and test state-of-the-art ML and AI methods, resolve problems, adapt, compare, iterate and collaborate.
• Demonstrate strong command of relevant analytic, ML, AI and biostatistical methods and the ability to find the best approaches for different situations.
• Pursue research on methods and applications while prioritizing the transition of insights to production use
• Partner closely with the risk modeling scientists, biostatisticians, clinical, and business specialists.
• Present novel scientific results at conferences and in peer-reviewed scientific journals
• Provide scientific and technical guidance to team members and collaborators while empowering and inspiring them to do their best work
• Take a mindful, transparent, and humane approach to your work.

Must haves:

• Ph.D. and at least four years of academic or industry experience
• A record of designing and validating creative solutions to complex quantitative problems as demonstrated by research publications or industry achievements
• Experience working with large, noisy, and confounded datasets
• Ability to effectively prioritize multiple competing development projects.
• Proficiency in implementing statistical/ML models in a general-purpose programming language.
• Excellent ability to communicate to technical peers and across disciplines, and to work collaboratively on interdisciplinary teams.
• A transparent, self-reflective approach that is comfortable with ambiguity, seeks to improve on or correct flaws in your own work, and is open to others’ suggestions
• A passion for innovation, demonstrated initiative in tackling new areas of research, and an ability to carry great ideas forward to practical and impactful implementation
• Experience with biological or healthcare data is preferred
• Facility reading and interpreting scientific and medical literature is preferred
• Experience with statistical study design is preferred
• Familiarity working in a Linux environment and with cloud computing infrastructure is preferred
• Experience in scientific parallel computing and/or in distributed computing environments like Kubernetes is preferred.

Benefits and additional information:

The US target range of our base salary for new hires is $157,250 - $240,000. You will also be eligible to receive pre-IPO equity, cash bonuses, and a full range of medical, financial, and other benefits dependent on the position offered. Please note that individual total compensation for this position will be determined at the Company’s sole discretion and may vary based on several factors, including but not limited to, location, skill level, years and depth of relevant experience, and education. We invite you to check out our career page @ https://careers.freenome.com/ for additional company information.

Freenome is proud to be an equal opportunity employer and we value diversity. Freenome does not discriminate on the basis of race, color, religion, marital status, age, national origin, ancestry, physical or mental disability, medical condition, pregnancy, genetic information, gender, sexual orientation, gender identity or expression, veteran status, or any other status protected under federal, state, or local law.