AppLovin seeks a mid-level Software Engineer with 4+ years experience in machine learning to develop and improve user signals, features, and recommendation models for a large-scale advertising platform. The role involves working on user signal representation, ranking, retrieval, model architecture, optimization, and scaling ML systems. Candidates must have strong programming skills, experience with PyTorch or TensorFlow, and expertise in deploying ML models in production. Responsibilities include developing scalable ML models, improving training and inference efficiency, building tools for model evaluation and deployment, and collaborating with cross-functional teams. Benefits include equity eligibility, medical, dental, vision, life, disability insurance, 401(k), unlimited discretionary time off, paid holidays, and sick leave. The position is full-time and on-site in Palo Alto, California.
What you'll do
Develop and improve user signals, features, and representations for large-scale machine learning models for advertising and recommendation
Similar jobs
More roles worth a look
Related opportunities based on specialty and working model so candidates can keep momentum.
Explore machine learning approaches to learn from large-scale, sparse, noisy, and heterogeneous user signals
Improve quality, coverage, and utilization of user signals and measure their impact on downstream models and advertising performance
Develop user representations and modeling approaches for ranking, retrieval, prediction, and optimization systems
Advance large-scale recommendation systems across candidate retrieval, ranking, prediction, and optimization
Explore new model architectures and learning approaches to improve recommendation quality and advertising performance
Develop scalable approaches for representation learning, feature interaction, and multi-task learning across large-scale user signals
Identify and solve ML problems related to user signal quality, feature quality, model quality, training stability, data integrity, and serving performance
Scale machine learning models and training systems to support increasing data volume, model complexity, and computational requirements
Improve training and inference efficiency by identifying bottlenecks in computation, data loading, memory, distributed execution, and hardware utilization
Build scalable tools and frameworks for user signal and feature evaluation, model training, experimentation, deployment, monitoring, and debugging
Design and analyze offline and online experiments to understand incremental value of user signals and model improvements on product and business outcomes
Collaborate with engineering, data, and product teams to bring new user signals and ML approaches from experimentation into production
Requirements
Bachelor's degree in Computer Science, Computer Engineering, Machine Learning, or related technical field, or equivalent practical experience
4+ years of experience developing and deploying machine learning systems in production environments
Experience with machine learning or deep learning in recommendation, ranking, retrieval, prediction, advertising, representation learning, or related applications
Experience developing and training machine learning models using large-scale datasets
Strong understanding of machine learning fundamentals including model architectures, optimization, representation learning, feature engineering, and model evaluation
Strong programming and software engineering skills with experience building reliable production systems
Experience with modern deep learning frameworks such as PyTorch or TensorFlow
Experience diagnosing and solving problems involving data and feature quality, model quality, training, or serving performance
