Machine Learning Engineer – Search Product

Website Twitter

Twitter Search is the search engine for Twitter: it’s the place to find the most relevant and engaging content for any topic or interest. We build products on top of a super realtime pipeline that processes nearly one trillion tweets from the whole of Twitter’s history, organizes the world’s conversation as it happens, and personalizes it to each individual user’s needs and context We connect users to the most relevant people and conversations around their interests. We need your help building this exciting product!

Twitter Search is responsible for producing content timelines for keywords, trends, hashtags, topics, realtime events, and even places and emojis. We are not only surfacing tweets, but also users, images, videos, as well as live events. What’s more, we provide features like spelling correction and query suggestions as you type, bringing you even closer to what you need. Twitter Search is also a powerful generic information retrieval system that drives many other products and internal applications at Twitter.

Who We Are

We are a distributed and collaborative team building the real-time Twitter search engine and working across areas such as machine learning, applied data science, recommendation systems, information retrieval systems, natural language processing, large graph analysis, anti-spam and anti-abuse. We put these skills to use finding, personalizing and organizing relevant content for users. We create algorithms by solving a wide range of problems in IR, NLP, and ML with the goal of understanding users’ intent through query and context, ranking and organizing content, and extracting insights to make suggestions for better navigation of content on Twitter.

What You Will Do

  • You will participate in the engineering life-cycle at Twitter, designing and implementing components, pipelines and algorithms related to machine learning.
  • Collect, clean up, analyze production and user data to draw insights and produce ideas, working alongside the data scientist in the team.
  • Collaborating in an engineering team, conducting code reviews and design reviews.
  • Writing code and tests for production services, offline jobs, and internal tools.
  • Conducting offline and online experiments.
  • Deploying and maintaining production services, participating in on-call rotations.
  • Collaborating across teams, working alongside our platform engineers and SREs.

Who You Are

You have a passion for machine learning and improving the ways people communicate and get informed about the world, live. You would like to solve problems in machine learning, information retrieval, text understanding, recommendation, user behavior understanding, and more. You have experience dealing with large data sets in a distributed environment. Also it would be great if you:

  • Have a good grasp of CS fundamentals, data structure, common algorithms.
  • Comfortable working with at least one OOP or functional language and one interpretive/script language, experience with Java, Scala, and Python a plus.
  • Have knowledge in one or more of the following fields: machine-learning, information retrieval, recommendation systems, NLP.
  • Knowledge of distributed systems and parallel computing.
  • Experience in collaborating across multiple teams including analytics, product management, and operations.


BS, MS, or PhD in Computer Science or equivalent work experience.

We are committed to an inclusive and diverse Twitter. Twitter is an equal opportunity employer. We do not discriminate based on race, color, ethnicity, ancestry, national origin, religion, sex, gender, gender identity, gender expression, sexual orientation, age, disability, veteran status, genetic information, marital status or any 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.

To apply for this job please visit