Who We Are: The Human in the Loop team is part of Cortex, the central machine learning organization at Twitter. Cortex’s mission is to empower internal teams to efficiently leverage machine learning by providing platform, modeling, and research expertise while advancing the ML technologies within Twitter.
We tackle Twitter-specific challenges by building techniques that leverage the best of machine learning with the best of human expertise. We apply and advance state-of-the-art machine learning techniques to invent new models and systems that can be used to help improve areas across all of Twitter’s business units.
We operate at scale whilst ensuring fair and ethical use of our models and data.
What you will do:
Apply your machine learning expertise to develop algorithms, modeling techniques, and tools to streamline human-in-the-loop model training processes. You will develop methods to optimize the value of user feedback and human annotation within an active learning framework. You will work closely with interface developers to construct well-designed human annotation tasks. You will architect machine learning pipelines to automate model retraining and deployment. You will implement mechanisms to automatically monitor and assess the quality of machine learning models that are updated in an online fashion.
You will collaborate with product teams to help them apply human-in-the-loop best practices in the context of their applications and use cases. As the authority on human-in-the-loop processes for machine learning, you will be able to influence the team’s roadmap and help product teams seek out new opportunities to leverage our machine learning technology and systems.
You will also be engaging with the research community via publications and conferences. Twitter, and our team, are suitably positioned to be thought leaders in the space of human-in-the-loop machine learning technology for social media content understanding.
Who you are: You have sound knowledge of state-of-the-art machine learning models (in particular deep learning models for NLP, computer vision or other areas relevant to social media platforms) and are capable of applying them to real-world problems. You understand best-practices for applying data collection and annotation techniques for training machine learning models. You are comfortable with building production-grade software systems, and are up-to-date with software engineering best practices. You are keen to continue learning and developing your expertise in machine learning.