Are you an engineer who’s interested in tackling very challenging adversarial problems and passionate about defending online users against abuse, spam, and manipulation? Do you love working on challenging problems that require a multi-disciplinary approach, creative solutions, and rapid product iterations? Will you be proud to work on a real-time, scalable system that serves millions of users daily? If so, you should join us.
Who We Are
The Health ML engineering team is responsible for building scalable detection systems that keep spam, manipulation, and abuse at bay. We use ML and relevance techniques to make Twitter safer and to limit the spread of misinformation on the platform. Our team works across the product to detect abusive and spammy users and content, increase action on bad actors, drive changes in user behavior, and detect and remediate accounts that are violating the terms of service on Twitter.
We develop, maintain, and contribute to several machine learning models and systems, including:
- Models that detect unwanted interactions
- Models to prioritize human review of accounts violating Twitter's policies to more quickly take action and limit their damage
- Detection of bots that misuse the platform or spread misinformation
- Detection of repeat abusive offenders who create new accounts after being suspended
- Real-time rule engines and clustering systems to identify and action on clusters of bad actors at scale
What You’ll Do
Although you will work on cutting-edge problems, this position is not a pure research position. You will participate in the engineering life-cycle at Twitter, including designing distributed systems, writing production code and data pipelines, conducting code reviews and working alongside our infrastructure and reliability teams. You’ll apply data science, machine learning, and/or graph analysis techniques to a variety of modeling and relevance problems involving users, their social graph, their tweets, and their behavior.
Who You Are
You’re a relevance engineer, applied data scientist, or machine-learning engineer who wants to work on exciting algorithmic and deep infrastructure issues to improve the health of the public conversation on Twitter. You’re experienced at solving large scale relevance problems and comfortable doing incremental quality work while building brand new systems to enable future improvements.
- You are experienced in one or more of the following: machine learning (including deep learning), information retrieval, recommendation systems, social network analysis.
- You are a strong technical advocate with a background in Java, C++, or Scala, and Python.
- Experience with a number of ML techniques and frameworks, e.g. data discretization, normalization, sampling, linear regression, decision trees, deep neural networks, etc
- 3+ years experience with one or more DL software frameworks such as Tensorflow, PyTorch, Theano
- You strive to find the right balance between moving fast to deliver quality improvements to users and accumulating technical debt that drags down productivity.
- You have a collaborative working style with a strong focus on disciplined execution and results.
- You like to ground decisions in data and reasoning and solve root causes of problems rather than surface issues.
- You are adept at communicating relevant information clearly and concisely.
- You look ahead to identify opportunities and thrive in a culture of innovation.
- M.S. or PhD in Computer Science or Machine Learning related degree; or equivalent work experience in the field
- 7+ years experience leading and delivering effective ML solutions for large scale production use cases.
We are committed to an inclusive and diverse Twitter. Twitter is an equal opportunity employer. We do not discriminate based on race, ethnicity, color, ancestry, national origin, religion, sex, sexual orientation, gender identity, age, disability, veteran, genetic information, marital status or any other legally protected status.