Sr. Software Engineer, Machine Learning & Data Infrastructure

As a Senior Software Engineer focused on Machine Learning and Data Infrastructure at OKX, you build and improve the ML and data infrastructure behind our risk and fraud prevention systems. You work hands-on to move models from experimentation into reliable production services, improve model execution performance, and develop data pipelines that support training, evaluation, and real-time decisions. You take ownership of your work, identify improvements proactively, and deliver with limited guidance.

What you'll do

• Improve model inference latency, throughput, resource utilization, and cost by profiling the prediction path from feature retrieval and preprocessing to model execution, implementing measurable improvements while preserving model quality.
• Build and maintain infrastructure for model packaging, versioning, deployment, serving, monitoring, and rollback across cloud platforms and regions.
• Develop and optimize offline data pipelines using Databricks, Apache Spark, and warehouse or lakehouse technologies, addressing data modeling, partitioning, joins, shuffles, skew, incremental processing, and cost.
• Work on offline and online feature pipelines, supporting point-in-time correctness, consistent feature definitions, freshness, lineage, and reproducible backfills.
• Build and maintain reliable feature services and data integrations for risk models and decision systems.
• Take ownership of projects and operational issues, communicate progress and tradeoffs, and collaborate with ML, data engineering, cloud infrastructure, security, and product teams.
• Contribute to technical discussions, share knowledge, and help teammates through code reviews and collaboration.

What you bring

• Experience building and operating distributed systems, ML infrastructure, or data platforms, with ownership of meaningful production components.
• Hands-on experience improving production model performance, such as latency, throughput, resource utilization, or cost.
• Strong experience with Databricks and Spark, or comparable offline data platforms, including execution plans, distributed query optimization, storage layouts, data correctness, and workload cost management.
• Experience with the model lifecycle, including training and serving integration, validation, deployment, observability, and rollback.
• Strong Python and SQL skills, plus proficiency in at least one backend or systems language such as Java, Scala, Go, or C++.
• Ability to work independently through loosely defined problems, make sound implementation decisions, and deliver maintainable systems with limited guidance.

Nice to have

• SageMaker, Alibaba Cloud PAI/EAS, or comparable ML platforms.
• Inference optimization using tools such as ONNX Runtime, TensorRT, or Triton.
• Delta Lake, MLflow, feature stores, Kafka, Flink, and low-latency data stores.
• Fraud detection or financial risk systems.
• Fluency in Mandarin.

What we offer

• Salary range of $178,888 to $268,333, plus performance bonus and long-term incentives.
• Comprehensive healthcare schemes for employees and dependants.
• Learning and development programs for growth and professional development.
• Wellness and meal allowances.
• Team building programs and company events.

About OKX

OKX is a leading crypto exchange and developer of OKX Wallet, providing millions with access to crypto trading and decentralized crypto applications. We serve hundreds of large institutions seeking access to crypto markets and are backed by our Proof of Reserves. We operate across multiple global offices, united by our core principles of We Before Me, Do the Right Thing, and Get Things Done.