1 day ago
Singapore (city not specified)Staff+
Responsibilities
- Optimize production model inference latency, throughput, resource utilization, and cost across feature retrieval, preprocessing, and model execution.
- Build reusable infrastructure for model packaging, versioning, deployment, serving, monitoring, and rollback across cloud platforms and regions.
- Design and optimize offline data pipelines using Databricks, Apache Spark, and warehouse or lakehouse technologies.
- Connect offline and online feature pipelines while maintaining point-in-time correctness, consistent feature definitions, freshness, lineage, and reproducible backfills.
- Develop reliable feature services and data integrations for risk models and decision systems.
- Set technical direction, mentor engineers, and lead delivery across ML, data engineering, cloud infrastructure, security, and product teams.
Requirements
- Experience building and operating large-scale distributed systems, ML infrastructure, or data platforms with technical ownership across teams.
- Hands-on experience optimizing production model performance with measurable improvements in latency, throughput, utilization, or cost.
- Deep understanding of Databricks and Spark or comparable offline data platforms, including execution plans, distributed query optimization, storage layouts, data correctness, and workload cost management.
- Experience across the model lifecycle, including training and serving integration, validation, deployment, observability, and rollback.
- Strong Python and SQL skills plus at least one backend or systems language such as Java, Scala, Go, or C++.
- Ability to turn ambiguous requirements into clear architecture and deliver maintainable systems through hands-on engineering and technical leadership.
- Helpful experience includes SageMaker, Alibaba Cloud PAI/EAS, ONNX Runtime, TensorRT, Triton, Delta Lake, MLflow, feature stores, Kafka, Flink, low-latency data stores, fraud detection, or financial risk systems.
Tech Stack
Categories
Data EngineeringML Engineering
About OKX
OKX builds a global cryptocurrency exchange and Web3 wallet used by retail and institutional traders for spot, derivatives, and DeFi access, with developer APIs. Its business model centers on trading and financing fees, plus wallet and on-chain services. Founded in 2017 and privately held, OKX publishes monthly proof-of-reserves and operates as part of the OKG group serving crypto markets worldwide.
