4 hours ago
Base Salary
$185k - $235k/yr
Responsibilities
- Design and own batch and streaming offline and online feature pipelines that transform raw user events into targeting and bidding features.
- Develop identity-prediction, user/content embedding, intent, conversion, and signal-quality or value models.
- Integrate model outputs into advertising targeting, bidding, and ranking models and own measurable business impact.
- Manage the full ML lifecycle, including data preparation, feature engineering, training, evaluation, deployment, monitoring, iteration, and A/B testing.
- Ensure features and model outputs meet the freshness, latency, reliability, and throughput requirements of real-time bidding.
- Build data quality, labeling, and validation systems and identify gaps, bias, and freshness issues in user signals.
- Collaborate with Ads, Data, and Infrastructure teams on signal and feature design.
- Drive technical direction, design reviews, engineering practices, and mentorship.
Requirements
- Bachelor's or Master's degree in Computer Science, Machine Learning, Statistics, or a related quantitative field, or equivalent practical experience.
- 5+ years of industry experience as an ML engineer or applied scientist building and shipping production ML models.
- Strong knowledge of feature engineering, supervised learning, embeddings or representation learning, and offline and online evaluation.
- Proficiency in Python and an ML stack such as PyTorch or TensorFlow, scikit-learn, and pandas/NumPy.
- Hands-on experience with large-scale data processing using tools such as Spark, Flink, SQL, or Presto/Trino.
- Experience taking models from concept through production training, deployment, monitoring, and metric-driven iteration.
- Strong analytical and problem-solving skills, including reasoning about model behavior, data quality, and business impact.
- Preferred: experience in advertising, recommendation, search, growth, targeting, bidding, ranking, CTR/CVR prediction, or identity prediction.
- Preferred: experience with behavioral data, event pipelines, user embeddings, online feature serving, feature stores, embedding or vector stores, and low-latency inference.
- Preferred: experience with Kafka, Flink, Spark Streaming, Hadoop, Hive, Presto/Trino, ML platforms, MLOps tooling, distributed training, embedding tables, quantization, or efficient serving.
Benefits
- Health, dental, and vision care for employees and families, with 100% employee coverage.
- 401(k) plan with company matching.
- Paid time off and paid holidays.
- FSA, HSA, and commuter benefits programs.
- Team activity budget.
- Competitive benefits and compensation package; the full-time role is described as a US position, with annual base pay of $185,000–$235,000 USD and possible discretionary bonus and options.
Tech Stack
Apache FlinkApache HadoopApache HiveApache KafkaApache SparkNumPyPandasPrestoPythonPyTorchscikit-learnSQLTensorFlow
Categories
Data EngineeringML Engineering
About NewsBreak
NewsBreak builds a local-news aggregation and discovery platform for U.S. consumers on web and mobile, powered by recommendation systems and NLP. It partners with publishers and independent creators and monetizes primarily through advertising for local and national businesses. Founded in 2015 and headquartered in Mountain View, California, the platform serves over 40 million monthly active users and aggregates content from more than 10,000 sources.