📍 Work Location: 98 Hoang Quoc Viet, Cau Giay, Hanoi

🕒 Working Hours: 8:30 AM – 5:30 PM (Monday to Friday)

💰 Salary Range: VND 30–70 million

What You’ll Do:

• Design and operate scalable, secure ML platform infrastructure supporting offline training, batch scoring, and real-time inference.
• Build and maintain core ML platform services such as model registry, versioning, champion/challenger workflows, feature ingestion and serving, and deployment orchestration.
• Standardize ML workflows from experiment → approval → production.
• Build and maintain CI/CD pipelines for ML and platform components, including automated deployment, environment promotion (UAT → Production), rollback, and recovery.
• Deploy and operate model serving systems via REST / gRPC APIs and batch scoring pipelines.
• Support advanced deployment strategies such as shadow, canary, and A/B testing.
• Ensure low latency, high availability, and strong observability for scoring services.
• Collaborate with Data Engineering teams to build and operate offline and online Feature Stores, ensuring feature consistency between training and serving.
• Design and implement monitoring for model performance, data quality, feature stability, and system health.
• Build early-warning mechanisms for model decay, data drift, and production anomalies.
• Support model governance, auditability, and compliance in credit-risk contexts.
• Work closely with Data Scientists, Risk, Fraud, Backend, and Infrastructure teams.
• Enable Data Science teams to move from notebook to production safely.

What We’re Looking For:

• Proven experience as an ML Platform Engineer, MLOps Engineer, or Platform / Software Engineer working with ML systems.
• Strong Python skills for platform services, automation, and ML tooling.
• Solid understanding of the ML lifecycle in production environments.
• Experience with containerization and orchestration (Docker, Kubernetes).
• Experience building and operating production APIs (FastAPI, gRPC).
• Strong understanding of batch and real-time scoring systems.
• Familiarity with CI/CD pipelines and infrastructure-as-code mindset.
• Strong system-thinking, with ability to design scalable, observable, and governed platforms.
• Excellent communication skills and strong ownership mindset.

Tech Stack (at a glance)

• Data & Storage: MinIO, Iceberg, ClickHouse
• Processing: Spark, Polars, Airflow, Pathway
• ML & MLOps: H2O.ai, MLflow
• Serving: FastAPI / gRPC
• Platform: Docker, Kubernetes, CI/CD (Git-based)
• Monitoring & Governance: Prometheus, Grafana, model & data observability

Nice to Have (Bonus)

• Experience in credit scoring, risk, fraud, or financial services.
• Experience with Feature Stores and Lakehouse-style data platforms.
• Experience with streaming or real-time data systems.
• Knowledge of model governance, approval workflows, and A/B testing for
• decision systems.

Why Join VC Scoring Team

• Build the core ML platform powering real financial decisions.
• Work on production-grade ML systems with high impact and responsibility.
• Own architectural decisions and influence long-term platform strategy.
• Collaborate with strong Data, Risk, and Engineering teams.