Loading...
Staff Machine Learning Engineer, Content Quality Signals at Pinterest
PinterestSan Francisco, CA, US; Remote, US·1w ago
LeadFull-timePythonAWSMachine LearningTensorFlowPyTorchMLNLP
Salary Range
$153,000 - $207,000 /year
This salary is estimated based on similar roles. The actual salary may vary.
About the Role
The Content Understanding team at Pinterest builds machine learning models that analyze images, text, and video to produce high-quality semantic signals. These signals power relevance and retrieval for Homefeed, Search, Related Pins, and Ads, and also support integrity use cases like spam and low-quality detection.
Key Responsibilities
- →Lead modeling strategy for content understanding, including architecture selection, training approach, and evaluation methodology.
- →Design and ship production models that generate content signals such as embeddings and classifications.
- →Own the full ML lifecycle: data/labeling strategy, training pipelines, offline evaluation, online experimentation, deployment, and monitoring/retraining.
- →Partner with infra/platform teams to ensure scalable, reliable training/serving.
- →Collaborate with signal-consuming teams to define signal contracts, adoption patterns, and success metrics.
- →Provide technical leadership through design reviews, mentoring, and raising the quality bar for modeling and ML engineering practices.
Requirements
- ✓M.S/PhD degree in Computer Science, Statistics or related field.
- ✓Significant industry experience building software and ML pipelines/systems, including technical leadership.
- ✓Strong proficiency in Python and at least one ML stack such as PyTorch/TensorFlow.
- ✓Proven experience training and deploying ML models to production.
- ✓Deep hands-on experience in content understanding domains, including computer vision, NLP, and multimodal models.
- ✓Experience working with large-scale datasets and distributed compute.
- ✓Strong applied skills in evaluation and experimentation.
- ✓Demonstrated ability to influence across teams and drive ambiguous problem areas to measurable outcomes.
