Phát triển, vận hành hệ thống ML end-to-end cho team Data Science từ feature, training đến serving.
Yêu cầu
Cử nhân CS/Data Science/SE hoặc ngành liên quan
0-2 năm kinh nghiệm data engineering, ML engineering, backend hoặc DevOps
Hiểu workflow ML (training, evaluation, deployment)
Python, SQL mạnh, viết code sạch, có test, maintainable
Biết Git, CI/CD, containerization, Linux
Trách nhiệm
Quản lý Feature Store, Label Store, model lifecycle (experiment tracking, registry, versioning)
Xây dựng, vận hành data pipeline batch/near real-time và Score Serving Layer (offline/online)
Thiết lập monitoring, alerting cho data quality, model performance (PSI, drift) và pipeline health
Xử lý incident production, thực hiện migration hệ thống, hỗ trợ data governance
Có thì tốt
Kinh nghiệm cloud platform (data warehouse, managed ML, container deployment), data transformation, workflow orchestrators
Kinh nghiệm feature store, model registry, ML monitoring tools
Kinh nghiệm monitoring, alerting, dashboarding, xây dựng web services/APIs
Lương và phúc lợi
Có lương tháng 13 và bonus hiệu suất lên đến 3 tháng
Cấp MacBook cho toàn bộ team kỹ thuật
Ngân sách BE Corp cho đi lại, ăn uống, đặt xe trên app Be
Khám sức khỏe hàng năm và bảo hiểm y tế cao cấp PTI sau thử việc
Tóm tắt bằng AI từ JD gốc, đọc JD gốc trước khi ứng tuyển.
About the Role
We’re looking for an engineer to develop, maintain and operate the end-to-end ML system of the Data Science team, from features and labels, through training and deployment, to the scores served to our products. You’ll work side by side with data scientists and help make their models reliable, reproducible and production-ready.
Responsibilities
Development: Feature, Label and Model Lifecycle
Manage and enrich the team’s Feature Store and Label Store: onboard new data sources, build reusable features, and ensure point-in-time correctness and consistency between training and serving.
Manage the model lifecycle: experiment tracking, model registry, versioning, validation, and promotion from development to production.
Build and improve internal tooling and libraries that make modeling work faster and more standardized.
Deployment: Pipelines and Score Serving
Build and operate data pipelines (batch and near real-time) that feed features into models and models into products.
Manage the Score Serving Layer, both offline (batch scoring) and online (real-time APIs), ensuring reliability, latency and correctness.
Maintenance: Monitoring, Incidents and Migration
Set up and maintain monitoring and alerting for data quality, model performance (PSI, score drift, etc.) and pipeline health.
Monitor models in production and keep them healthy: track score drift and performance degradation, investigate root causes, and trigger retraining or rollback when metrics breach thresholds.
Respond to and resolve production incidents: triage alerts, fix issues across pipelines and the Score Serving Layer, and put guardrails in place to prevent recurrence.
Plan and execute system migrations: move pipelines, models and services across environments, platforms or infrastructure with minimal downtime and no loss of correctness.
Governance
Help the team build up data governance to manage data and ensure data security: data lineage, documentation, access control, and data usage across models and partners.
Collaborate with and be mentored by specialist teams (e.g., Data Platform and Security) to apply data governance and security best practices.
Keep this information organized and up to date so the Lead and Manager can make informed decisions.
Requirements
Must-have
Bachelor’s degree in Computer Science, Data Science, Software Engineering or a related field.
0–2 years of experience in data engineering, ML engineering, backend or DevOps, or strong projects/internships demonstrating equivalent skills.
Understanding of the ML workflow (training, evaluation, deployment).
Strong Python and SQL; comfortable writing clean, tested, maintainable code.
Familiarity with version control, CI/CD, containerization and Linux-based environments.
Ownership mindset: you care about what happens after code is merged.
Nice-to-have
Experience with a major cloud platform (data warehouse, managed ML services, container deployment), data transformation tools, or workflow orchestrators.
Experience with feature stores, model registries or ML monitoring tools.
Experience with monitoring, alerting and dashboarding tools.
Building and operating web services or APIs.
Interest in financial services or credit scoring.
Why you’ll enjoy this role
Work on a real production ML system end-to-end, with guidance from experienced engineers and data scientists.
Clear growth path toward ML Platform Engineer or Senior MLE.
Freedom to improve how the team builds and ships models.
Our benefits
Competitive compensation including a 13th-month wage and up to 3 months of performance-based bonus.
MacBooks for all technical team members.
BE Corp budget (varies by level) for transportation, food and car bookings in the Be app.
Annual health checks and premium medical healthcare (PTI) after probation.
15 days of annual leave.
Quarterly and annual company trips, team-building and happy hour events.
