Backend Engineer Graduate (Recommendation Architecture) - 2026 Start (PhD)

Our Recommendation Architecture Team is responsible for building and optimizing the architecture of the recommendation system to provide the most stable and best experience for users. The team focuses on optimizing the recommendation system architecture, ensuring stability and high availability, and improving the performance of both online services and offline data flows. Collaborating with the algorithm team, we work to enhance recommendation effectiveness and user experience, boost system performance while reducing costs, build data and service mid‑platforms, and realize flexible and scalable high‑performance storage and computing systems.

Responsibilities

• Strategy Management and Optimization: Build an intelligent system to standardize recommendation strategies, perform long‑term and offline evaluation, automatically identify and retire ineffective strategies, and remove related code configurations.
• Adaptive Tuning and Fault Diagnosis: Leverage large model capabilities to optimize parameters and configurations of systems and underlying components for diverse business loads, and explore adaptive fault diagnosis solutions to provide global perspective for fault tracking, localization, and analysis.
• Cost‑Efficiency Balance: Address the high costs of model training and operation when applying generative technologies to recommendation systems, balancing costs and efficiency to achieve effective recommendation within limited resources.
• Cross‑Domain Data Processing: Handle massive heterogeneous data in horizontal cross‑domain scenarios, improve and ensure data quality and accuracy, standardize data supply for cross‑domain recommendation models, enable low‑cost cross‑terminal services, and ensure data privacy, security, and compliance.
• Data Storage and Quality Enhancement: Develop low‑cost, high‑performance storage engines, design flexible schema‑evolution mechanisms, achieve high‑concurrency real‑time data writing and training‑inference consistency, and build data‑model correlation analysis tools and automated training‑data processing pipelines based on the DCAI concept.
• Multimodal Data and Heterogeneous Computing: Construct a multimodal data heterogeneous computing framework for recommendation systems to solve challenges in data reading, framework integration, and high‑performance operator orchestration, improve data processing and model training efficiency, and establish a developer ecosystem centered on Python.
• Large‑scale Computing Model Efficiency Optimization for Recommendation: Co‑design with architecture and algorithm engineers to balance computing overhead and effectiveness gains for large‑scale recommendation models powered by large models in CV, NLP, and multimodal fields.

Qualifications

• Must be able to commit to an onboarding date by the end of 2026 and provide graduation date.
• Individuals completing or who have recently completed a PhD in Software Development, Computer Science, Computer Engineering, or a related technical discipline.
• Priority to candidates with in‑depth research results and extensive practical experience in relevant fields such as natural language processing, computer vision, data modeling, or algorithm optimization.
• Excellent programming abilities with a strong command of data structures and fundamental algorithms; proficiency in C/C++ is required for traditional coding roles, while proficiency in Python is required for intelligent coding roles.
• Ability to effectively communicate and collaborate with team members—including algorithm engineers, data analysts, and product managers—to explore new technologies and drive innovation in e‑commerce generative recommendation systems.

This position is part of the Recommendation Architecture Team at ByteDance.