Software Engineer, ML

Twitch•Seattle, WA

43d

About The Position

Join the Monetization ML team within Twitch's Commerce organization, where we're building the intelligent systems that power personalized experiences for creators and viewers across all monetization products. We are the team behind the ML infrastructure for ads, commerce, and money products - systems that optimize revenue and detect fraud while serving millions of users in real-time. From production model infrastructure to API integrations across services, we're constantly pushing the boundaries of what's possible in live streaming monetization. Our team are based in Seattle, WA and New York City, NY

Requirements

1+ 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
Proficiency in modern programming languages (Python, Java, Go) and distributed system technologies
A track record of building APIs and integrating systems that handle high-throughput, low-latency requirements
Understanding of data processing pipelines and experience with streaming technologies (Flink, Kafka, or similar)
Sharp problem-solving skills with a focus on algorithms, data structures, and distributed system design
Bachelor's degree in Computer Science, Engineering, or equivalent real-world experience

Nice To Haves

Familiarity with Twitch's tech stack: Golang, Python, Apache Flink, Cond
Experience with workflow orchestration tools like Airflow or Conductor for managing ML pipelines
Experience with AWS technologies like ECS, DynamoDB, Lambda, SQS, and Step Functions
Knowledge of real-time ML serving systems and model deployment at scale
Experience with fraud detection, recommendation systems, or monetization optimization
A passion for gaming, streaming, or the Twitch platform

Responsibilities

Build robust ML infrastructure and platforms that power personalized monetization experiences across Twitch's ecosystem
Architect and develop APIs that seamlessly integrate ML models with existing monetization services, enabling real-time and batch predictions at scale
Collaborate with Applied Scientists to productionize ML models, transforming research into production-ready systems that serve millions of users
Partner with product engineering teams across monetization to deliver ML-powered features that enhance creator and viewer experiences
Design and implement comprehensive monitoring and operational excellence systems for ML model performance, ensuring reliability and quality at scale
Develop data ingestion and processing pipelines that support both real-time inference and batch training workflows
Explore and build infrastructure for emerging use cases including LLM applications in monetization contexts