About the team
The Advertising Performance group focuses on performance for all participants in the Advertising ecosystem - Advertisers, Publishers, and Roku. The systems and solutions span multiple disciplines and technologies to perform real-time multi-objective optimization across large-scale distributed systems with low latency. We use Machine Learning, Reinforcement Learning, AI, Control and Optimization Systems, and Auction Dynamics to solve a large set of complex problems. At the core of this is our Machine Learning, Experimentation, and Inference Platform, which powers the entire landscape, and we continuously evolve.
About the role
We're on a mission to build cutting-edge advertising technology that empowers businesses to run sustainable and highly profitable campaigns. The Ad Performance team owns server technologies, data, and cloud services designed to improve the ad experience. We're looking for seasoned engineers with machine learning backgrounds to support this mission. Examples of problems include improving ad relevance, inferring demographics, optimizing yield, and more. Employees in this role are expected to apply knowledge of experimental methodologies, statistics, optimization, probability theory, and machine learning using both general-purpose software and statistical languages.
For California Only - The estimated annual salary for this position is between $229,500 - $367,100 annually. Compensation packages are based on factors unique to each candidate, including but not limited to skill set, certifications, and specific geographical location. This role is eligible for health insurance, equity awards, life insurance, disability benefits, parental leave, wellness benefits, and paid time off.
What you'll be doing
- ML infrastructure: Help build a first-class machine learning platform from the ground up, which manages the entire model lifecycle - feature engineering, model training, versioning, deployment, online serving/evaluation, and monitoring prediction quality
- Data analysis and feature engineering: Apply your expertise to identify and generate features that can be leveraged by multiple use cases and models
- Model training with batch and real-time prediction scenarios: Use machine learning and statistical modeling techniques such as Decision Trees, Logistic Regression, Neural Networks, Bayesian Analysis and others to develop and evaluate algorithms for improving product/system performance, quality, and accuracy
- Production operations: Low-level systems debugging, performance measurement, and optimization on large production clusters
- Collaboration with cross-functional teams: Partner with product managers, data scientists, and other engineers to deliver impactful solutions
- Staying ahead of the curve: Continuously learn and adapt to emerging technologies and industry trends
We're excited if you have
- Bachelor's, Master's, or PhD in Computer Science, Statistics, or a related field
- 5 years of experience in applied machine learning on real use cases
- Proficient coding skills and strong software development experience in Spark, Python, or Java
- Familiarity with real-time evaluation of models with low latency constraints
- Familiarity with distributed ML frameworks such as Spark-MLlib, TensorFlow, etc.
- Ability to work with large-scale computing frameworks, data analysis systems, and modeling environments i.e., Spark, Hive, NoSQL stores such as Aerospike and ScyllaDB
- Ad Tech experience is preferred
- Proficient use of AI tools and agentic coding practices
#LI-DH2