Lead Software Engineer - ML Infrastructure

San Francisco /
Engineering /
About Unlearn

Recent progress in artificial intelligence coupled with a growing resource of longitudinal patient data from historical clinical trials and real world sources provides an unprecedented opportunity to transform clinical trials and speed the development of new medicines.  

Unlearn is a science-first company that has invented the first machine learning platform for creating Digital Twins of patients in clinical trials — comprehensive simulations that answer “what would likely happen to this patient if he/she were randomized to the control group?”.

Using information from Digital Twins to estimate treatment effects with PROCOVA™ reduces required sample sizes, increases statistical power, and provides patient-level treatment response information. 

It’s about increasing confidence in trial results. 

It’s about bringing new medicines to patients faster.

It's about time.

Role Responsibilities:

• Lead the development of critical components of Unlearn’s growing disease-progression modeling software platform, incorporating,
- data management infrastructure,
- ETL pipelines,
- ML training and testing infrastructure,
- pipeline deployment and testing.
• Collaborate with data scientists and ML engineers to architect software solutions that meet the needs of the broader organization.
• Exemplify best practices/methods, for reproducible, traceable, and validatable data processing and ML pipelines.

Your Qualifications:

    • You are an experienced software engineer who wants to help build a new, computationally-focused approach to important problems in healthcare.
    • 6+ years work experience as a software engineer with emphasis on serving data science and machine learning workflows.
    • Capable of being a technical leader who can help direct important engineering projects. 
    • Experience with ETL and ML pipeline implementation and maintenance.
    • Fluent in Python, and Python data science ecosystem tools.
    • Demonstrated proficiency in writing high-quality code in a collaborative setting.
    • Experience operationalizing data science and machine learning algorithms.
    • An eye for ensuring production quality in critical software.
    • Experience with AWS services.
    • Eventually (after the pandemic) able to work in the downtown SF office at least 2 days per week.
You will be collaborating with the talented folks who are working to productionize and scale Unlearn’s technology. Your primary responsibility will be the development and maintenance of Unlearn’s data processing and ML infrastructure, making it possible to scale our production workflows by an order of magnitude. You’ll be relied upon to exemplify high standards of software development, and in particular best practices related to building and automating complex ML pipelines. You will have outsized impact throughout the technical organization, laying the groundwork for scale.

Compensation & benefits

Unlearn offers compensation commensurate with experience as well as a competitive benefits package, including:

Generous equity participation
Unlimited PTO plus company holidays
Annual company-wide shutdown between Christmas and New Years holidays
Professional development budget to attend conferences or other events
401k plan with generous matching
Company-subsidized medical, dental, & vision insurance plans
Commuter benefits plan
Paid Parental Leave

Unlearn is not currently offering visa sponsorships for any position. Please only apply if authorized to work in the U.S.

Unlearn is an equal opportunity employer. We embrace diversity and create an inclusive work environment because inclusion and diversity are essential to achieving our mission to create AI to simulate biology and improve patients' lives.

Pursuant to the San Francisco Fair Chance Ordinance, we will consider for employment qualified applicants with arrest and conviction records.

All employees who work at Unlearn must comply with our COVID-19 vaccination requirement or receive an approved exemption.