Applied Scientist - Safety ML

Twitch is the world’s biggest live streaming service, with global communities built around gaming, entertainment, music, sports, cooking, and more. It is where thousands of communities come together for whatever, every day.

We’re about community, inside and out. You’ll find coworkers who are eager to team up, collaborate, and smash (or elegantly solve) problems together. We’re on a quest to empower live communities, so if this sounds good to you, see what we’re up to on LinkedIn and X,  and discover the projects we’re solving on our Blog. Be sure to explore our Interviewing Guide to learn how to ace our interview process.

We are looking for applied scientists to solve challenging and open-ended problems in the domain of user and content safety. As an applied scientist on Twitch's Community team, you will use machine learning to develop data products tackling problems such as harassment, spam, and illegal content. You will use a wide toolbox of ML tools to handle multiple types of data, including user behavior, metadata, and user generated content such as text and video. You will collaborate with a team of passionate scientists and engineers to develop these models and put them into production, where they can help Twitch's creators and viewers succeed and build communities.

You will report to our Senior Applied Science Manager in San Francisco, CA. You can work from San Francisco, CA or Seattle, WA.

• Build machine learning products to protect Twitch and its users from abusive behavior such as harassment, spam, and violent or illegal content.
• Work backwards from customer problems to develop the right solution for the job, whether a classical ML model or a state-of-the-art one.
• Collaborate with Community Health's engineering and product management team to productionize your models into flexible data pipelines and ML-based services.
• Continue to learn and experiment with new techniques in ML, software engineering, or safety so that we can better help communities on Twitch grow and stay safe.

• 2+ years of hands-on industry experience building models for NLP, deep learning, bot detection, anomaly detection or in another practical ML domain.
• 2+ years experience writing high quality code to ship those models in production systems.
• PhD / MSc Degree in Computer Science, Mathematics, Statistics, Physics, Engineering, or similar quantitative field OR equivalent hands on experience. 
• Expertise with: Python and SQL, modern open source ML libraries (Pytorch, Tensorflow, etc.). 
• Familiarity with operating in AWS or similar cloud-computing services.

• PhD with a specialization in Machine Learning.
• 1+ years of experience working in the safety or fraud prevention domain (not necessarily as a scientist).
• Experience communicating with both technical and non-technical partners and stakeholders.
• Familiarity with Twitch, its business, and its community.

• Medical, Dental, Vision & Disability Insurance
• 401(k)
• Maternity & Parental Leave
• Flexible PTO
• Amazon Employee Discount

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

Job ID: TW9077