Job Duties: Be responsible for the development of state-of-the-art applied machine learning projects for one of the 3 modeling problems in ads ranking: lightweight ranker, engagement modeling and conversion modeling. Design features and build large-scale machine learning models to improve user ads action prediction with low latency. Develop new techniques for inferring user interests from online and offline activity. Mine text, visual, user signals to better understand user intention. Work with product and sales teams to design and implement new ad products. Partial telecommuting permitted.

Minimum Requirements: PhD, or foreign equivalent, in Computer Science, Information Systems, or a closely related field, and six months of experience in job offered or related software engineering/machine learning engineering role.

Special Skill Requirements:

(1)            Experience processing and analyzing large-scale structured and unstructured datasets used in machine learning and recommendation systems, including building and maintaining distributed data pipelines, performing data extraction and transformation, aggregating high-volume user interaction data, and ensuring data quality and scalability for model training and evaluation.

(2)            Applying machine learning techniques to design, build, train, evaluate, and improve predictive models for recommendation and ranking systems, including feature engineering, algorithm selection, model validation, hyperparameter tuning, and iterative optimization based on business and performance metrics.

(3)            Developing and deploying deep learning models for large-scale recommendation use cases, including designing neural network architectures, training models on high-dimensional data, optimizing model performance, and improving recommendation quality through representation learning, embedding-based methods, and other deep learning approaches.

(4)            Using natural language processing techniques to extract, represent, and model textual information for recommendation and related machine learning applications, including text preprocessing, tokenization, embedding generation, semantic modeling, and applying language-based features to improve relevance, ranking, personalization, or content understanding.

(5)            Hands-on experience using PyTorch to build, train, evaluate, and deploy machine learning and deep learning models, including implementing custom model architectures, managing large-scale training workflows, handling data loading and batching, debugging training issues, and optimizing model performance for production use.

(6)            Using Python for software development, machine learning model implementation, data processing, experimentation, automation, and pipeline development, including writing maintainable and scalable code for data analysis, model training, evaluation, and production system support.

(7)            Using C++ to develop and optimize performance-sensitive software components, including building efficient backend or systems-level functionality, improving runtime performance for large-scale applications, and supporting production environments where low-latency and high-throughput processing are required.

(8)            Using software version control systems to manage source code, collaborate across engineering teams, track changes, support code reviews, maintain release quality, and enable reliable development workflows for machine learning systems and production software.

(9)            Applying large language modeling techniques to machine learning and recommendation-related problems, including working with transformer-based models, language representations, fine-tuning or adapting pretrained models, and leveraging large language models to improve content understanding, personalization, retrieval, ranking, or related intelligent system capabilities.

(10)        Using Amazon Web Services (AWS) to support development, training, deployment, and operation of large-scale machine learning and recommendation systems, including working with cloud-based compute, storage, and data processing services to enable scalable experimentation, model training, data pipeline management, and production infrastructure.

Salary: $301,600.00 - $ 389,753.00 per annum

Reference #: L25-165711

This position is not available for relocation assistance.