Software Engineer, Safety ML

Amazon•San Francisco, CA

1d•Onsite

About The Position

As a software engineer on Twitch’s Safety ML team, you will leverage machine learning to develop the systems that keep the everyday Twitch user safe from abuse such as harassment, spam, and illegal content. You will collaborate with a passionate team of scientists and engineers to build the systems necessary to train, evaluate, and productionize our various models. You will build the tools and systems necessary to integrate these models into various parts of the Twitch experience to protect our users from harm. Our team is based in San Francisco, CA.

Requirements

5+ years of non-internship professional software development experience
5+ years of programming with at least one software programming language experience
5+ years of leading design or architecture (design patterns, reliability and scaling) of new and existing systems experience
Experience as a mentor, tech lead or leading an engineering team
3+ years of professional software development experience with a focus on building scalable systems
Experience building production ML infrastructure, including model deployment, serving, and monitoring systems
Experience with cloud technologies (AWS, GCP, Azure) and containerization software (Docker, Kubernetes, etc.)
Proficiency in Go, Python, and distributed systems technologies
Excellent written and verbal communication skills
Experience mentoring and supporting fellow engineers or interns
Bachelor's degree in Computer Science or related field or equivalent industry experience as a Software Engineer

Nice To Haves

Experience with model development
Proficiency with modern open source ML libraries (Pytorch, Tensorflow, ONNX, etc.)
Experience with workflow orchestration technologies (Airflow) for managing ML pipelines
Familiarity with Twitch, either as a viewer or creator (or both!)

Responsibilities

Design, build, and deploy reliable and performant services to protect Twitch and its users from abusive behavior such as harassment, spam, and violent or illegal content
Collaborate with Community Health’s science and product management team to productionize and scale models into ML-based services to be used across Twitch.
Design and build performant and reliable systems that handle multiple types of data, such as user behavior, metadata, and user generated content at scale for model development
Deliver high-quality code, tests, and documentation
Mentor other engineers on best practices within the ML space