Machine Learning Engineer - Platform Health
Remote - US / Canada
GitHub's many features give it a broad attack surface that make it a popular target for malicious hackers, spammers, and fraudsters. Hackers know that we protect the key intellectual property of a massive number of companies and people. Spammers love the many vectors for delivering rich content through the platform: from creating spam on Gists, issue comments, and user profiles to even opening Pull Requests to add ads to repositories. Fraudsters seek to profit by abusing GitHub and third-party integrators for monetary gain. This large and varied attack surface gives GitHub a somewhat unique set of problems to solve.
The mission of the Platform Health team is to protect the health, safety, and integrity of the GitHub platform from abuse at scale - establishing and preserving trust for the users, communities, integrators, and businesses that rely on GitHub. As a member of GitHub's Platform Health team you will use data to understand and detect abuse, build systems to automate detection, shape data collection processes, and advise product teams on best practices for making their products more resilient to abuse.
The Platform Health team is self-driven and autonomous while being highly collaborative. This is a talented team that values learning, work-life balance, and tackling interesting challenges - something in no short supply given our adversarial, evolving problem space. The team's strength lies in the culture of high trust and empathy in which we operate; and genuine joy in the work we do and people we work with.
- Build classifiers (rule-based and machine learned) to detect illegitimate content and behavior
- Conduct exploratory analysis to identify new patterns of illegitimate content and behavior
- Participate in design and execution of hand labeling (account review) processes
- Work closely with engineers to define requirements for tooling improvements
- Update classifiers to manage evolution of behavior in near-real-time
- Partner with other internal teams at GitHub to solve problems at scale
- Reviewing new products and providing consultation to product teams
Note: In this position, you may encounter pornographic or abusive content. On-call work may be required.
- Experience building high-precision, productionized models
- Strong data analysis skills
- Experience with content analysis, pattern recognition, or applied statistics
- Excellent written and verbal communication skills
- A working knowledge of regular expressions and SQL
- Experience in detecting spam, fraud, or abusive activity at scale
- Experience building content and behavior classifiers (rule-based or machine-learned)
- Experience using Git and GitHub
- Practical software development skills, especially in Ruby and Python
- Background in Computer Science, Math/Finance, Physics, Applied Economics, Statistics or other technical field
Who We Are:
GitHub is the developer company. We make it easier for developers to be developers: to work together, to solve challenging problems, and to create the world’s most important technologies. We foster a collaborative community that can come together—as individuals and in teams—to create the future of software and make a difference in the world.
Customer Obsessed - Trust by Default - Ship to Learn - Own the Outcome - Growth Mindset - Global Product, Global Team - Anything is Possible - Practice Kindness
Why You Should Join:
At GitHub, we constantly strive to create an environment that allows our employees (Hubbers) to do the best work of their lives. We've designed one of the coolest workspaces in San Francisco (HQ), where many Hubbers work, snack, and create daily. The rest of our Hubbers work remotely around the globe. Check out an updated list of where we can hire here: https://github.com/about/careers/remote
We are also committed to keeping Hubbers healthy, motivated, focused and creative. We've designed our top-notch benefits program with these goals in mind. In a nutshell, we've built a place where we truly love working, we think you will too.
GitHub is made up of people from a wide variety of backgrounds and lifestyles. We embrace diversity and invite applications from people of all walks of life. We don't discriminate against employees or applicants based on gender identity or expression, sexual orientation, race, religion, age, national origin, citizenship, disability, pregnancy status, veteran status, or any other differences. Also, if you have a disability, please let us know if there's any way we can make the interview process better for you; we're happy to accommodate!
Please note that benefits vary by country. If you have any questions, please don't hesitate to ask your Talent Partner.