Software Engineer, ML Infrastructure, Snap

• Strong programming skills in Python, Java, Scala, or C++
• Strong problem-solving skills with a focus on system performance, data quality, and scalability
• Deep understanding of distributed systems, data pipelines, and ML infrastructure
• Experience with big data processing frameworks such as Spark, Flink, Dataflow, or Ray
• Familiarity with feature engineering, signal pipelines, and model training workflows
• Proven track record of operating highly available and reliable infrastructure at scale
• Ability to proactively learn new concepts and apply them in a fast-paced environment
• Strong collaboration skills with ML engineers, data scientists, and infra teams
• Bachelor’s degree in a technical field such as computer science or equivalent experience
• 6+ years of post-Bachelor’s software development experience; or Master’s degree in a technical field + 5+ years of post-grad software development experience; or PhD in a relevant technical field + 2+ years of post-grad software development experience
• Experience building large-scale data or ML production systems, distributed systems, or big data processing

Desirable

• Snap Engineering teams build fun and technically sophisticated products that reach hundreds of millions of Snapchatters around the world, every day. We’re deeply committed to the well-being of everyone in our global community, which is why our values are at the root of everything we do
• You’ll play a critical role in scaling our Content Signal & Training Data infrastructure, developing new signals for ranking and retrieval, optimizing training data pipelines, and driving innovations that make Snapchat’s ranking and recommendation systems more reliable, efficient, and impactful
• We’re looking for a Software Engineer, Content Signal & Training Data Infrastructure to join Snap Inc!
• Design and optimize systems for large-scale signal generation, indexing, serving, and applications
• Build and maintain content feature lifecycle management, including generation, storage, sourcing, monitoring, and deprecation of unused features
• Simplify the content feature development process by collaborating with ML data platform teams and improving tooling for generation, storage, and sourcing
• Optimize and monitor signal pipelines for reliability, latency, and scalability
• Develop infrastructure for training data pipelines, including logjoin optimization, streaming logjoin, data sampling, data shuffling, and window tuning
• Build and maintain training data for new applications and ranking models, including experiments on long-term objectives such as user retention and creator affinity
• Collaborate with ML engineers to improve training workflows (feature engineering, preprocessing, model iterations, evaluation, and inference)
• Build training data monitoring and analysis tools with Bento and data infra teams, including SQL-based analysis, feature importance, discrepancy detection, and anomaly detection