Twitter, Inc. (NYSE: TWTR) is the best and fastest place to see what’s happening and what people are talking about all around the world. From breaking news and entertainment to sports and politics, from big events to everyday interests. If it’s happening anywhere, it’s happening first on Twitter. Twitter is where the full story unfolds with all the live commentary and where live events come to life unlike anywhere else. Twitter is available in more than 40 languages around the world. The service can be accessed at Twitter.com and on a variety of devices. For more information, visit about.twitter.com

Company Highlights

• Founded in 2006
• Headquarters in San Francisco, CA
• Revenue in 2020: $3.72B
• 70% of users are international
• 7000+ employees globally

Twitter is seeking a Staff Backend Software Engineer, Machine Learning for Birdwatch, our pilot program in a new crowdsourced/participatory approach to reducing misleading information. Birdwatch pushes the state-of-the-art in approaching misleading information on the Internet and we employ a deeply experimental, fast-moving, and iterative approach to find product solutions that work for customers.

We are looking for someone who can work across backend and machine learning systems — designing, developing and launching services that power core features of Birdwatch, efficient and reliable data pipelines, and production machine learning systems. You need not have equal experience across backend, data pipelines, and ML systems — if you have significant experience in one area, and some experience (or interest) in the others, that can work.

You’ll work as part of a cross-functional team including machine learning, engineering, data science, research, design, product, and even academic experts outside the company who study the space.

What You’ll Do:

As we bring Birdwatch to the world, you will play a critical role in scaling and launching the core algorithms, data pipelines and backend services that power Birdwatch in real-time, including:

• Compute contributor helpfulness scores that are resistant to adversaries and bad actors, e.g. using iterative graph propagation algorithms in a similar style as PageRank, or explicit coordinated manipulation/spam detection

• Detect rater similarity/diversity and polarization, using techniques such as matrix factorization to learn user embeddings or similarities

• Develop and operate real-time data pipelines in support of the note scoring and reputation algorithms that power Birdwatch

• Design elements of our backend architecture. Focus on enabling rapid iteration to validate product hypotheses, and ensuring a plan for broader, scalable designs if hypotheses are validated

• Build and design novel user-facing product experiences

• Partner with client teams to define APIs, and potentially even assist in building client code and product experiences

• Drive communication and coordination with partner teams (from Health to Legal to Core Services to API, etc).

• Open-sourcing as much of our core algorithmic code as possible, in the spirit of Birdwatch’s transparency

• B.S., M.S., and/or PhD in Computer Science or a related technical field, or equivalent experience

• 5+ years of experience in backend systems or distributed systems/large scale data processing

• Experience and familiarity with the modern data pipeline and ML infrastructure ecosystem

• Great understanding of one or more of the following: Scala, C++, or Java

Bonus qualifications (but not necessary):

• Experience owning a production machine learning system and/or pipeline

• Basic familiarity with statistics and machine learning, especially in relevant domains e.g. graph algorithms, matrix factorization, using human-in-the-loop data, bad actor/manipulation modeling, game theory, interpretable and fair ML, active learning, etc.

• Proficiency with Python and SQL

Who You Are:

• You’ve built and maintained a large-scale distributed system and/or machine learning data pipeline

• Passion for the problem of misleading information & creating a better informed world

• Enjoy a rapid iterative approach / the 0-to-1 experience

• Enioy working in an ambiguous space with no known product solutions, and trailblazing to build novel solutions that work

• Ability to move fast and get things done, and help the broader team do so (to enable rapid iteration on the product)

• Comfortable (maybe even excited) to work with a distributed team

• You are experienced with software engineering best practices and bring a disciplined approach to testing and driving reductions in technical debt

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.

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