Backend Engineer, AML Framework Development (Search, Ads, and Recommendation Direction)

ByteDance
Singapore
Workplace: OnsiteFull timeFunction: Software EngineeringEducation: bachelorsSkills: []

Build and scale model inference services for large-parameter AI models supporting ads ranking, search ranking, and live/e-Commerce recommendations. Own the architecture and R&D of the inference framework, including scheduling, monitoring/alerting, and canary release, while addressing performance, resource, and stability bottlenecks under high concurrency. Stay current on inference technologies, drive technical innovation and framework standardization, and support efficient model launches across business scenarios.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
ByteDance
ByteDance
1 month ago

Backend Engineer, AML Framework Development (Search, Ads, and Recommendation Direction)

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 30 days agoStatus: Live
Reposted: similar role first listed 1 month ago

Job Summary

Build and scale model inference services for large-parameter AI models supporting ads ranking, search ranking, and live/e-Commerce recommendations. Own the architecture and R&D of the inference framework, including scheduling, monitoring/alerting, and canary release, while addressing performance, resource, and stability bottlenecks under high concurrency. Stay current on inference technologies, drive technical innovation and framework standardization, and support efficient model launches across business scenarios.
Location: Singapore
Workplace: Onsite
Employment Type: Full time
Job Function: Software Engineering
Seniority: Entry level

Key Responsibilities

  • •Design and implement architecture for model inference services, building scalable, highly available enterprise inference systems for large-parameter AI models.
  • •R&D and optimize core inference framework modules (e.g., inference engine scheduling, monitoring/alerting, and canary release) and address performance/resource/stability bottlenecks.
  • •Continuously iterate on framework performance in high-concurrency and large-model inference scenarios to improve efficiency and reliability.
  • •Track emerging inference technologies, select and innovate technologies aligned with business scenarios, and standardize the team’s technical system.
  • •Develop distributed high-concurrency service architecture solutions and support efficient model launches across business scenarios.

Key Requirements

  • •Bachelor’s degree in Computer Science (or equivalent) with at least 1 year of relevant experience.
  • •Solid C/C++ programming skills plus knowledge of data structures and algorithms; familiarity with Linux commands.
  • •Proficiency in multi-threaded concurrency concepts, including threads, synchronization locks, and thread pools, with basic performance tuning skills.
  • •Excellent programming skills with solid understanding of data structures; proficient in Python and familiar with C++.
  • •Experience in R&D projects involving high-concurrency distributed services, including service latency and resource optimization.
Experience:AI infrastructureRecommendation systemsHigh-concurrency distributed servicesR&DLarge-scale inference
Education:Bachelor's in Computer Science
Tech Stack:LinuxCC++PythonRedisRocksDBBRPCGRPCGPUMulti-threaded concurrencyThread poolsCanary releaseMonitoring and alerting

Company Brief

ByteDance
Develops consumer internet and content platforms, including TikTok and other apps for short-form video, news, and entertainment. It also builds advertising, commerce, and creator tools that connect audiences, brands, and publishers across global markets.
Industry: Digital Media
Company Size: Enterprise (1,001+ employees)
Revenue: USD 1B+
Growth: Established Company
Headquarters: Beijing, China
Founded: 2012
WebsiteLinkedIn